{
  "data": {
    "tool": {
      "category": "",
      "endpoint": "https://ratchetgate.com/mcp",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ratchetgate-ratchet.json",
      "kind": "mcp",
      "listed": "indexed",
      "liveUrl": "https://www.anchorterminal.com/api/v1/live/ratchetgate-ratchet.json",
      "markdownUrl": "https://www.anchorterminal.com/tools/ratchetgate-ratchet.md",
      "mcpTools": {
        "check": {
          "checker": "anchor-check/1.0",
          "totalTokens": 4885,
          "counts": {
            "error": 0,
            "note": 1,
            "warn": 10
          },
          "findings": [
            {
              "rule": "TC11",
              "severity": "warn",
              "tool": "ratchet_extend_lease",
              "message": "2 parameters without a description: effect_id, lease_token",
              "fix": "Describe each one: format, units, an example, and what happens when it's left out."
            },
            {
              "rule": "TC11",
              "severity": "warn",
              "tool": "ratchet_get_effect",
              "message": "1 parameter without a description: idempotency_key",
              "fix": "Describe each one: format, units, an example, and what happens when it's left out."
            },
            {
              "rule": "TC11",
              "severity": "warn",
              "tool": "ratchet_get_group",
              "message": "its one parameter, group_key, has no description",
              "fix": "Describe each one: format, units, an example, and what happens when it's left out."
            },
            {
              "rule": "TC11",
              "severity": "warn",
              "tool": "ratchet_list_effects",
              "message": "3 parameters without a description: limit, run_id, state",
              "fix": "Describe each one: format, units, an example, and what happens when it's left out."
            },
            {
              "rule": "TC11",
              "severity": "warn",
              "tool": "ratchet_reconcile_effects",
              "message": "1 parameter without a description: effect_type",
              "fix": "Describe each one: format, units, an example, and what happens when it's left out."
            },
            {
              "rule": "TC11",
              "severity": "warn",
              "tool": "ratchet_report_effect",
              "message": "3 parameters without a description: effect_id, lease_token, outcome",
              "fix": "Describe each one: format, units, an example, and what happens when it's left out."
            },
            {
              "rule": "TC11",
              "severity": "warn",
              "tool": "ratchet_resolve_effect",
              "message": "3 parameters without a description: effect_id, outcome, result",
              "fix": "Describe each one: format, units, an example, and what happens when it's left out."
            },
            {
              "rule": "TC13",
              "severity": "warn",
              "tool": "ratchet_begin_effect",
              "message": "compensation.payload (object with no properties), payload (object with no properties)",
              "fix": "Declare the properties (or additionalProperties with a schema) and the array's items."
            },
            {
              "rule": "TC13",
              "severity": "warn",
              "tool": "ratchet_report_effect",
              "message": "result (object with no properties)",
              "fix": "Declare the properties (or additionalProperties with a schema) and the array's items."
            },
            {
              "rule": "TC13",
              "severity": "warn",
              "tool": "ratchet_resolve_effect",
              "message": "result (object with no properties)",
              "fix": "Declare the properties (or additionalProperties with a schema) and the array's items."
            },
            {
              "rule": "TC24",
              "severity": "note",
              "message": "15 of 15 tools have no outputSchema",
              "fix": "Declare outputSchema for tools that return structured data, and return structuredContent that matches it."
            }
          ]
        },
        "checkedAt": "2026-10-04T22:23:37Z",
        "count": 15,
        "note": "answered without the initialize handshake",
        "schemaTokens": 4885,
        "status": "ok",
        "tools": [
          {
            "name": "ratchet_get_circuit",
            "title": "Check whether surge containment is holding your work",
            "description": "Call this when a begin returned \"approval_required\" or \"denied\" and the reason mentions a circuit breaker. A breaker opens when an effect type is being performed far more often than its configured hourly ceiling — usually because something is looping.\n\nWhat to do with the answer:\n- If a breaker is open, STOP creating effects of that type. Retrying will not help and each attempt is recorded.\n- resets_at tells you when it closes itself. If it is null, a human opened it deliberately and only a human will close it — do not wait, and do not poll.\n- Report the reason to your operator and stop. Do not attempt to work around it by renaming the effect type, splitting the work across keys, or using a different idempotency key: that defeats a safety control that exists to protect the people your actions reach.\n- effect_type \"*\" means every effect type in the workspace is stopped.",
            "inputSchema": {
              "additionalProperties": false,
              "properties": {},
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "Check whether surge containment is holding your work"
            }
          },
          {
            "name": "ratchet_begin_effect",
            "title": "Ask permission to perform a side effect",
            "description": "Call this IMMEDIATELY BEFORE performing any side effect that touches the outside world (sending a message, charging a card, creating a resource, writing to someone else's system). Returns a decision you MUST obey. If the response carries budget_warning, a spend ceiling exists but nothing was counted toward it — surface that to the operator rather than ignoring it. If it carries integration_warning, you have been beginning effects without reporting them: call ratchet_report_effect after every action, and tell the operator, because the effects already begun will start being blocked.\nDecisions:\n- \"execute\": you hold the lease. Perform the action now, then call ratchet_report_effect.\n  If the response carries vendor_idempotency_key, send that key to the vendor as ITS own idempotency key (the response says where it goes). Where enforced is true the vendor itself will then refuse a duplicate, which protects the action even if some other caller skips this gate entirely.\n- \"duplicate\": this action ALREADY HAPPENED. Do NOT perform it. Use the returned `result` as though you had just done the work.\n- \"in_flight\": another process is doing it right now. Do NOT perform it. Wait `retry_after_seconds` and ask again.\n- \"blocked\": an earlier attempt may or may not have taken effect. Do NOT perform it. Tell the user what is unresolved, or verify at the vendor and call ratchet_resolve_effect.\n- \"approval_required\": a human must approve. Do NOT perform it.\n- \"denied\": policy or budget refused it. Do NOT perform it.\nThe idempotency_key must be derived deterministically from the work itself so that a retry of the same logical action produces the same key. Never use a random value or the current time.",
            "inputSchema": {
              "properties": {
                "agent_id": {
                  "description": "Identifier for you, the calling agent.",
                  "type": "string"
                },
                "compensates_effect_id": {
                  "description": "Set when THIS call IS an undo, naming the effect it reverses. Comes from ratchet_unwind_group.",
                  "type": "string"
                },
                "compensation": {
                  "description": "How to undo THIS step if the workflow has to be rolled back. Declare it now, while you still know what undoing means — it cannot be worked out later. Steps without one are permanent.",
                  "properties": {
                    "effect_type": {
                      "description": "e.g. \"booking.cancel\", \"payment.refund\"",
                      "type": "string"
                    },
                    "payload": {
                      "additionalProperties": true,
                      "description": "What the undo will need — booking ids, charge ids.",
                      "type": "object"
                    }
                  },
                  "required": [
                    "effect_type",
                    "payload"
                  ],
                  "type": "object"
                },
                "dimensions": {
                  "additionalProperties": {
                    "type": "string"
                  },
                  "description": "Who or what this action is aimed at, most often the destination: {\"counterparty\":\"acct_1234\"}. SEND THIS whenever the action targets a specific recipient, account or customer. It is how a per-destination ceiling can exist at all — \"no more than $200 to any one counterparty per day\" — and only a keyed hash of the value is stored, so Ratchet counts the destination without ever being able to read it. Declaring can only tighten: it never removes a limit. If begin is refused with dimension_required, the operator has made a dimension mandatory for this effect type and you must send it.",
                  "type": "object"
                },
                "effect_type": {
                  "description": "Namespaced kind of side effect, e.g. \"email.send\", \"payment.charge\", \"github.pr.create\". Policy is configured per type.",
                  "pattern": "^[a-z0-9]([a-z0-9._-]{0,62}[a-z0-9])?$",
                  "type": "string"
                },
                "estimated_cost_micros": {
                  "description": "What this action will cost at the third party, in micro-USD (1000000 = $1). ALWAYS SEND THIS when the action costs money. Spend ceilings are computed from it, and a ceiling with nothing declared against it never fires — the operator would be relying on a limit that cannot trigger. If the response contains budget_warning, that is exactly what has happened: tell the operator. Ratchet does not collect this money; it only counts it. It can also route the action to a human: an operator may set an approval threshold, and an action whose declared cost reaches it comes back approval_required instead of execute — so declaring accurately is what keeps large actions reviewable. Where a threshold is set, omitting this is refused with cost_required rather than allowed.",
                  "minimum": 0,
                  "type": "integer"
                },
                "group_key": {
                  "description": "Use when this action is one step of a multi-step workflow that must succeed or fail as a whole, e.g. \"booking:trip_8812\". Lets the whole unit be rolled back later.",
                  "type": "string"
                },
                "idempotency_key": {
                  "description": "Deterministic identifier for this specific logical action, e.g. \"welcome-email:user_123\" or \"invoice:2026-08:acct_88123\". The SAME action retried must produce the SAME key.",
                  "maxLength": 255,
                  "minLength": 1,
                  "type": "string"
                },
                "lease_seconds": {
                  "description": "How long you expect the action to take. Report before this elapses or the effect becomes indeterminate.",
                  "maximum": 3600,
                  "minimum": 5,
                  "type": "integer"
                },
                "payload": {
                  "additionalProperties": true,
                  "description": "The action's parameters. Only a hash is stored — the raw content never persists. Reusing a key with different parameters is rejected, which catches key collisions.",
                  "type": "object"
                },
                "run_id": {
                  "description": "Groups all effects from one task or run.",
                  "type": "string"
                },
                "vendor": {
                  "description": "Which vendor performs this effect (e.g. \"stripe\", \"square\", \"adyen\"). Shapes vendor_idempotency_key so it satisfies that vendor's rules.",
                  "maxLength": 32,
                  "type": "string"
                }
              },
              "required": [
                "effect_type",
                "idempotency_key"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": false,
              "openWorldHint": false,
              "readOnlyHint": false,
              "title": "Ask permission to perform a side effect"
            }
          },
          {
            "name": "ratchet_report_effect",
            "title": "Report the outcome of an effect you executed",
            "description": "Call this IMMEDIATELY AFTER performing an action that ratchet_begin_effect authorised. Pass the lease_token you were given.\nReport \"succeeded\" with a result — future duplicate callers replay that result instead of repeating the action.\nReport \"failed\" ONLY when you are certain the action did NOT reach the outside world (for example, a validation error before the request was sent). That permits a clean retry.\nIf you are UNSURE whether it went through — a timeout, a dropped connection, an ambiguous error — do NOT report anything. Say so to the user. Letting the lease lapse records an honest \"indeterminate\", which is far safer than a false \"failed\" that licenses a duplicate.",
            "inputSchema": {
              "properties": {
                "actual_cost_micros": {
                  "description": "What it really cost, if different from the estimate.",
                  "minimum": 0,
                  "type": "integer"
                },
                "effect_id": {
                  "type": "string"
                },
                "failure_reason": {
                  "description": "Required when outcome is \"failed\".",
                  "type": "string"
                },
                "lease_token": {
                  "type": "string"
                },
                "outcome": {
                  "enum": [
                    "succeeded",
                    "failed"
                  ],
                  "type": "string"
                },
                "result": {
                  "additionalProperties": true,
                  "description": "What the action produced (ids, confirmation numbers, links). Replayed verbatim to duplicate callers, so include what a retry would need.",
                  "type": "object"
                }
              },
              "required": [
                "effect_id",
                "lease_token",
                "outcome"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": false,
              "openWorldHint": false,
              "readOnlyHint": false,
              "title": "Report the outcome of an effect you executed"
            }
          },
          {
            "name": "ratchet_extend_lease",
            "title": "Say you are still working on an effect",
            "description": "Call this periodically during a long action you were authorised to perform, before the lease expires. It tells Ratchet you are alive and extends your hold.\nUse it when work turns out to take longer than the lease you asked for — a slow vendor, a large export, a retrying upload. Without it, the lease expires while you are still working, the effect is recorded as having an UNKNOWN outcome, and your report is then refused.\nIf it fails with lease_expired or lease_lost, STOP. Your hold is gone and the outcome is already recorded as unknown. Do not keep going and do not retry the action — call ratchet_begin_effect to find out where things actually stand.",
            "inputSchema": {
              "properties": {
                "effect_id": {
                  "type": "string"
                },
                "extend_seconds": {
                  "description": "How much longer you need, from now. Clamped to the policy maximum.",
                  "maximum": 3600,
                  "minimum": 5,
                  "type": "integer"
                },
                "lease_token": {
                  "type": "string"
                }
              },
              "required": [
                "effect_id",
                "lease_token"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": false,
              "openWorldHint": false,
              "readOnlyHint": false,
              "title": "Say you are still working on an effect"
            }
          },
          {
            "name": "ratchet_get_effect",
            "title": "Check whether an action has already been done",
            "description": "Look up the recorded state of an action WITHOUT reserving a lease and without consuming your plan allowance. Use it to answer \"did I already do this?\" — for example when resuming after a crash, or when a user asks whether something went through. To actually perform work, use ratchet_begin_effect instead; this tool never grants permission.",
            "inputSchema": {
              "properties": {
                "effect_type": {
                  "description": "Namespaced kind of side effect, e.g. \"email.send\", \"payment.charge\", \"github.pr.create\". Policy is configured per type.",
                  "pattern": "^[a-z0-9]([a-z0-9._-]{0,62}[a-z0-9])?$",
                  "type": "string"
                },
                "idempotency_key": {
                  "type": "string"
                }
              },
              "required": [
                "effect_type",
                "idempotency_key"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "Check whether an action has already been done"
            }
          },
          {
            "name": "ratchet_resolve_effect",
            "title": "Settle an effect whose outcome was unknown",
            "description": "Use ONLY after you have checked the third-party system and now know what really happened to an effect that was left \"indeterminate\". Record \"succeeded\" if the action did occur, \"failed\" if it did not, or \"cancelled\" to abandon it. Include how you verified it in `evidence`. Never guess: resolving incorrectly is exactly the duplicate or lost action this service exists to prevent.",
            "inputSchema": {
              "properties": {
                "effect_id": {
                  "type": "string"
                },
                "evidence": {
                  "description": "How you verified the real outcome. Stored in the audit trail.",
                  "type": "string"
                },
                "outcome": {
                  "enum": [
                    "succeeded",
                    "failed",
                    "cancelled"
                  ],
                  "type": "string"
                },
                "result": {
                  "additionalProperties": true,
                  "type": "object"
                }
              },
              "required": [
                "effect_id",
                "outcome"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": false,
              "openWorldHint": false,
              "readOnlyHint": false,
              "title": "Settle an effect whose outcome was unknown"
            }
          },
          {
            "name": "ratchet_get_run",
            "title": "What have I already done in this run?",
            "description": "Recall the work already gated under a run id, before doing anything that might repeat it. Call this FIRST when resuming a task — after a restart, a handoff, or when your context has been compacted and you are no longer certain what you did. It returns what succeeded with the recorded results, what is still in flight, what failed, and — separately, because it is the only category that can hurt you — what has an unknown outcome. Anything under \"done\" has already happened: use its result rather than performing it again. Costs about a seventeenth of the context of listing the same effects.",
            "inputSchema": {
              "properties": {
                "run_id": {
                  "description": "The run id you passed to ratchet_begin_effect for this task.",
                  "maxLength": 128,
                  "type": "string"
                }
              },
              "required": [
                "run_id"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "What have I already done in this run?"
            }
          },
          {
            "name": "ratchet_list_effects",
            "title": "List recent gated effects",
            "description": "Review recent effects for this workspace, optionally filtered by state or run. Use it to find unresolved work — filter by state \"indeterminate\" to see every action whose outcome is unknown and still needs verification.",
            "inputSchema": {
              "properties": {
                "effect_type": {
                  "description": "Namespaced kind of side effect, e.g. \"email.send\", \"payment.charge\", \"github.pr.create\". Policy is configured per type.",
                  "pattern": "^[a-z0-9]([a-z0-9._-]{0,62}[a-z0-9])?$",
                  "type": "string"
                },
                "limit": {
                  "maximum": 100,
                  "minimum": 1,
                  "type": "integer"
                },
                "run_id": {
                  "type": "string"
                },
                "state": {
                  "enum": [
                    "awaiting_approval",
                    "pending",
                    "succeeded",
                    "failed",
                    "indeterminate",
                    "denied",
                    "cancelled"
                  ],
                  "type": "string"
                }
              },
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "List recent gated effects"
            }
          },
          {
            "name": "ratchet_get_policy",
            "title": "Read the policy for an effect type",
            "description": "Shows how this workspace has configured a given effect type: whether it is allowed, how long a lease lasts, the attempt ceiling, spend limits, the approval threshold above which an action waits for a human, and — most importantly — what happens when an attempt ends indeterminate. Check this before designing a retry strategy.",
            "inputSchema": {
              "properties": {
                "effect_type": {
                  "description": "Namespaced kind of side effect, e.g. \"email.send\", \"payment.charge\", \"github.pr.create\". Policy is configured per type.",
                  "pattern": "^[a-z0-9]([a-z0-9._-]{0,62}[a-z0-9])?$",
                  "type": "string"
                }
              },
              "required": [
                "effect_type"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "Read the policy for an effect type"
            }
          },
          {
            "name": "ratchet_unwind_group",
            "title": "Roll back a multi-step unit of work",
            "description": "Call this when a multi-step workflow fails partway and the steps that already succeeded must be undone — a booking made but not paid for, a resource created but not configured.\nReturns the exact compensations to perform, in the order to perform them, which is the REVERSE of the order they succeeded in. Undoing forwards can strand a step that depended on an earlier one.\nRatchet does NOT perform the compensations. For each step: call ratchet_begin_effect with the step's suggested_idempotency_key and compensates_effect_id, do the real undo, then call ratchet_report_effect. Gating the undo is what stops a retry from refunding twice.\nRead `unresolved` first. If any effect in the group has an unknown outcome, STOP and resolve it before undoing anything around it. Read `irreversible` too: those steps succeeded and declared no way to undo themselves, so a human has to decide what to do about them. Say so plainly rather than implying the rollback was complete.",
            "inputSchema": {
              "properties": {
                "group_key": {
                  "description": "The unit of work to roll back, e.g. \"booking:trip_8812\".",
                  "type": "string"
                },
                "reason": {
                  "description": "Why it is being rolled back. Stored for the operator.",
                  "type": "string"
                }
              },
              "required": [
                "group_key"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": false,
              "openWorldHint": false,
              "readOnlyHint": false,
              "title": "Roll back a multi-step unit of work"
            }
          },
          {
            "name": "ratchet_get_group",
            "title": "Inspect a unit of work",
            "description": "Shows every step in a multi-step unit of work: what succeeded, what can still be undone, what has already been undone, what is irreversible, and what has an unknown outcome. Use it to answer \"where did this workflow actually get to?\" after a crash, without changing anything.",
            "inputSchema": {
              "properties": {
                "group_key": {
                  "type": "string"
                }
              },
              "required": [
                "group_key"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "Inspect a unit of work"
            }
          },
          {
            "name": "ratchet_get_usage",
            "title": "Check plan, credit balance, and spend",
            "description": "Returns the current plan, remaining included effects for the month, prepaid credit balance, and today's declared external spend against each budget ceiling. Use it to warn a user before a long run exhausts an allowance or a budget.",
            "inputSchema": {
              "properties": {},
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "Check plan, credit balance, and spend"
            }
          },
          {
            "name": "ratchet_list_receipts",
            "title": "Get signed proof of the decisions on an effect",
            "description": "Returns a signed receipt for every decision made about one effect, refusals included. Each signature is over the exact bytes in `body` and verifies offline against the Ed25519 key published at /.well-known/ratchet-receipt-key — you do not have to trust this server to check them. Use this when a human asks you to PROVE an action was or was not authorised, rather than asserting it.",
            "inputSchema": {
              "properties": {
                "effect_id": {
                  "description": "The effect to fetch receipts for.",
                  "type": "string"
                }
              },
              "required": [
                "effect_id"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "Get signed proof of the decisions on an effect"
            }
          },
          {
            "name": "ratchet_reconcile_effects",
            "title": "Find real-world actions that bypassed the gate",
            "description": "Given the idempotency keys for actions a vendor says actually happened, returns which ones went through Ratchet and which it has never seen. The unseen ones are code paths that acted WITHOUT asking, so a retry there can act twice — a bug the operator almost certainly does not know about. Send references only; never send credentials.",
            "inputSchema": {
              "properties": {
                "effect_type": {
                  "type": "string"
                },
                "keys": {
                  "description": "Idempotency keys your system should have used for those actions.",
                  "items": {
                    "type": "string"
                  },
                  "maxItems": 1000,
                  "type": "array"
                }
              },
              "required": [
                "effect_type",
                "keys"
              ],
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "Find real-world actions that bypassed the gate"
            }
          },
          {
            "name": "ratchet_get_prevented_loss",
            "title": "What the gate has actually saved",
            "description": "Counts duplicate actions refused in the last 30 days and what they would have cost. Only counts refusals where a cost was declared on the effect, so it under-reports rather than flatters. IMPORTANT: pass estimated_cost_micros on ratchet_begin_effect or this reads zero — the number is only as good as what callers declare. This is money not spent at your vendors, never money paid to Ratchet.",
            "inputSchema": {
              "properties": {},
              "type": "object"
            },
            "annotations": {
              "destructiveHint": false,
              "idempotentHint": true,
              "openWorldHint": false,
              "readOnlyHint": true,
              "title": "What the gate has actually saved"
            }
          }
        ]
      },
      "name": "ratchet",
      "note": "Indexed from the official MCP registry: facts and our own checks, not reviewed, so no score, grade or rank.",
      "packages": [
        {
          "registryType": "npm",
          "identifier": "ratchet-mcp",
          "version": "0.3.0",
          "transport": "stdio"
        }
      ],
      "pageJsonUrl": "https://www.anchorterminal.com/tools/ratchetgate-ratchet.json",
      "popularity": {
        "githubStars": 0,
        "npmWeekly": 36
      },
      "registryName": "com.ratchetgate/ratchet",
      "remotes": [
        {
          "type": "streamable-http",
          "url": "https://ratchetgate.com/mcp"
        }
      ],
      "repository": "https://github.com/thearchitect0x-glitch/ratchet",
      "reviewed": false,
      "slug": "ratchetgate-ratchet",
      "source": "the official MCP registry",
      "sourceUrl": "https://registry.modelcontextprotocol.io/v0.1/servers?search=com.ratchetgate/ratchet",
      "summary": "Your agent asks before it acts, so the same real-world action is attempted at most once.",
      "updatedAt": "2026-09-10T23:44:12Z",
      "url": "https://www.anchorterminal.com/tools/ratchetgate-ratchet",
      "vendor": "ratchetgate.com",
      "vendorUrl": "https://ratchetgate.com",
      "version": "0.3.0",
      "websiteUrl": "https://ratchetgate.com",
      "where": "both",
      "why": [
        "vendor"
      ]
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/tools/ratchetgate-ratchet",
    "json": "https://www.anchorterminal.com/tools/ratchetgate-ratchet.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/tools/ratchetgate-ratchet.md",
    "slim": "https://www.anchorterminal.com/tools/ratchetgate-ratchet.min.md"
  },
  "markdown": "# ratchet\n\n\u003e Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/\n\n- Kind: MCP server, by ratchetgate.com (https://ratchetgate.com)\n- Listed because: It's published in the registry under ratchetgate.com, a namespace the registry only gives to whoever proves they control that domain.\n- What the official MCP registry says: Your agent asks before it acts, so the same real-world action is attempted at most once.\n\n## Facts\n\n- MCP registry: `com.ratchetgate/ratchet` 0.3.0\n- Endpoint: https://ratchetgate.com/mcp (streamable HTTP)\n- Package: npm `ratchet-mcp` (stdio)\n- Source: https://github.com/thearchitect0x-glitch/ratchet\n- Website: https://ratchetgate.com\n- npm downloads a week: 36\n- GitHub stars: 0\n- Registry entry updated: 2026-09-10\n\n## Tools\n\n- Tools it lists (15, about 4,885 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:23 UTC):\n  - `ratchet_get_circuit` (read-only): Call this when a begin returned \"approval_required\" or \"denied\" and the reason mentions a circuit breaker. A breaker opens when an effect type is being…\n  - `ratchet_begin_effect` (writes): Call this IMMEDIATELY BEFORE performing any side effect that touches the outside world (sending a message, charging a card, creating a resource, writing to…\n  - `ratchet_report_effect` (writes): Call this IMMEDIATELY AFTER performing an action that ratchet_begin_effect authorised. Pass the lease_token you were given. Report \"succeeded\" with a result —…\n  - `ratchet_extend_lease` (writes): Call this periodically during a long action you were authorised to perform, before the lease expires. It tells Ratchet you are alive and extends your hold. Use…\n  - `ratchet_get_effect` (read-only): Look up the recorded state of an action WITHOUT reserving a lease and without consuming your plan allowance. Use it to answer \"did I already do this?\" — for…\n  - `ratchet_resolve_effect` (writes): Use ONLY after you have checked the third-party system and now know what really happened to an effect that was left \"indeterminate\". Record \"succeeded\" if the…\n  - `ratchet_get_run` (read-only): Recall the work already gated under a run id, before doing anything that might repeat it. Call this FIRST when resuming a task — after a restart, a handoff, or…\n  - `ratchet_list_effects` (read-only): Review recent effects for this workspace, optionally filtered by state or run. Use it to find unresolved work — filter by state \"indeterminate\" to see every…\n  - `ratchet_get_policy` (read-only): Shows how this workspace has configured a given effect type: whether it is allowed, how long a lease lasts, the attempt ceiling, spend limits, the approval…\n  - `ratchet_unwind_group` (writes): Call this when a multi-step workflow fails partway and the steps that already succeeded must be undone — a booking made but not paid for, a resource created…\n  - `ratchet_get_group` (read-only): Shows every step in a multi-step unit of work: what succeeded, what can still be undone, what has already been undone, what is irreversible, and what has an…\n  - `ratchet_get_usage` (read-only): Returns the current plan, remaining included effects for the month, prepaid credit balance, and today's declared external spend against each budget ceiling.…\n  - `ratchet_list_receipts` (read-only): Returns a signed receipt for every decision made about one effect, refusals included. Each signature is over the exact bytes in `body` and verifies offline…\n  - `ratchet_reconcile_effects` (read-only): Given the idempotency keys for actions a vendor says actually happened, returns which ones went through Ratchet and which it has never seen. The unseen ones…\n  - `ratchet_get_prevented_loss` (read-only): Counts duplicate actions refused in the last 30 days and what they would have cost. Only counts refusals where a cost was declared on the effect, so it…\n- How its tools read to an agent (0 errors, 10 warnings, 1 note, about 4,885 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):\n  - warn TC11 ratchet_extend_lease: 2 parameters without a description: effect_id, lease_token\n  - warn TC11 ratchet_get_effect: 1 parameter without a description: idempotency_key\n  - warn TC11 ratchet_get_group: its one parameter, group_key, has no description\n  - warn TC11 ratchet_list_effects: 3 parameters without a description: limit, run_id, state\n  - warn TC11 ratchet_reconcile_effects: 1 parameter without a description: effect_type\n  - warn TC11 ratchet_report_effect: 3 parameters without a description: effect_id, lease_token, outcome\n  - warn TC11 ratchet_resolve_effect: 3 parameters without a description: effect_id, outcome, result\n  - warn TC13 ratchet_begin_effect: compensation.payload (object with no properties), payload (object with no properties)\n  - warn TC13 ratchet_report_effect: result (object with no properties)\n  - warn TC13 ratchet_resolve_effect: result (object with no properties)\n  - note TC24 server: 15 of 15 tools have no outputSchema\n\n- JSON: https://www.anchorterminal.com/api/v1/tools/ratchetgate-ratchet.json\n- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-05",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Terminal",
        "url": "https://www.anchorterminal.com/tools/"
      },
      {
        "name": "Indexed",
        "url": "https://www.anchorterminal.com/indexed/"
      },
      {
        "name": "ratchet",
        "url": ""
      }
    ],
    "description": "ratchet, an MCP server by ratchetgate.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Your agent asks before it acts, so the same real-world action is attempted at most once.",
    "facts": [
      "not reviewed",
      "not ranked",
      "facts only"
    ],
    "h1": "ratchet",
    "image": "https://www.anchorterminal.com/assets/og/indexed.png",
    "path": "/tools/ratchetgate-ratchet",
    "published": "",
    "section": "indexed",
    "title": "ratchet: MCP server, indexed from the official MCP registry",
    "toc": null,
    "updated": "2026-10-05",
    "url": "https://www.anchorterminal.com/tools/ratchetgate-ratchet"
  },
  "tokens": {
    "markdown": 1500,
    "slim": 1430
  },
  "version": 1
}