# Overwing (slim) > Overwing, an MCP server by overwing.ai, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm. - Full: https://www.anchorterminal.com/tools/overwing-mcp.md (~2,350 tokens) · this version ~2,280 tokens · JSON https://www.anchorterminal.com/tools/overwing-mcp.json · canonical https://www.anchorterminal.com/tools/overwing-mcp - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05 # Overwing > 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/ - Kind: MCP server, by overwing.ai (https://overwing.ai) - Category: Guardrails & safety filters (https://www.anchorterminal.com/categories/guardrails.md) - Listed because: It's published in the registry under overwing.ai, a namespace the registry only gives to whoever proves they control that domain. - What the official MCP registry says: Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm. ## Facts - MCP registry: `ai.overwing/mcp` 0.12.0 - Endpoint: https://overwing.ai/mcp (streamable HTTP) - Package: npm `overwing-mcp` (stdio) - Source: https://github.com/frod27/overwing-mcp - Website: https://overwing.ai - npm downloads a week: 948 - GitHub stars: 0 - Registry entry updated: 2026-10-02 ## Tools - Tools it lists (34, about 6,650 tokens of context, `tools/list` without credentials over MCP 2026-07-28, checked 2026-10-04 22:20 UTC): - `evaluate` (writes): Works with no API key: 10 evaluations a day, inputs up to 2,000 characters, and the text is not stored. With a key: 250 a day and up, inputs up to 100,000… - `evaluate_batch` (writes): Score up to 50 texts against one rule set in a single call. Each item counts as one evaluation. Returns a summary plus per-item verdicts; items can fail… - `list_rule_sets` (read-only): List the prebuilt and custom rule sets available to this organization. Needs an organization key. - `get_rule_set` (read-only): Fetch a rule set with its full rule definitions. Use 'content-safety' as a worked example when writing your own. Needs an organization key. - `create_rule_set` (writes): Create a custom rule set with 1 to 25 rules. Each rule is a choice (pick one option), score (position on an ordered scale), or noul (yes/no) question with a… - `get_evaluation` (read-only): Fetch a stored evaluation by id, including the original input and per-rule results. Needs an organization key. - `list_evaluations` (read-only): List recent evaluations, newest first, with optional verdict and rule set filters. Use next_cursor to page. Needs an organization key. - `get_usage` (read-only): Daily usage, remaining quota for today, and plan limits. Needs an organization key. - `whoami` (read-only): Identify the organization and plan behind the API key on this request, the key's scope, the organization's data settings (store_inputs, retention_days), and… - `create_account` (writes): Create an Overwing account for yourself, with no email: an organization and an API key, returned once. Nothing is sent to anyone. Use it when you have no key… - `prove_domain` (writes): Begin proving that your account controls a domain. For an account with no email the domain stands in for one: it raises the limits to the normal free tier,… - `verify_domain` (writes): Look for the value prove_domain asked for, at the domain. Found: the domain is the account's. Not found: an error saying what was looked for; DNS changes can… - `list_plans` (read-only): Public plan catalog: prices, daily limits, and per-minute burst limits. No API key needed. - `atlas_lookup` (read-only): Say what a User-Agent string claims to be and whether the claim can be trusted, from the Overwing Atlas registry of AI crawlers, fetchers and browser agents.… - `atlas_agents` (read-only): Browse or search Overwing Atlas, the registry of AI crawlers, fetchers and browser agents: name, operator, user-agent tokens, Web Bot Auth key directory,… - `atlas_register_agent` (writes): Add an agent or crawler you operate to the Overwing Atlas registry, free, so a site that looks up its User-Agent learns who runs it. Give the agent's name, the… - `atlas_verify_registration` (writes): Look for the proof at the operator's domain: the DNS TXT record or the file that atlas_register_agent asked for. Found: the entry is published in the registry,… - `atlas_list_registrations` (read-only): The agents this organization has registered in Overwing Atlas, newest first, each with its status (pending_verification, pending_review, published, rejected)… - `atlas_withdraw_registration` (writes): Withdraw a registration. A published entry leaves the registry, so lookups stop naming the agent; an unfinished request is abandoned. This cannot be undone:… - `atlas_summary` (read-only): Public numbers from Overwing Atlas: registry counts by purpose and verification, published browser-agent traffic shares, sector field-scan headlines (e.g. how… - `beacon_start` (writes): Overwing Beacon answers one question about a site: is this product reachable by agents? It checks robots.txt rules for AI agents, llms.txt, the sitemap, the… - `beacon_report` (read-only): The report for a check started with beacon_start. The first call runs the check. With an Overwing key on the connection: score (0 to 100), verdict (yes,… - `beacon_sample` (read-only): A real Overwing Beacon report, free: the check of overwing.ai itself, refreshed daily. Read it to see exactly what a full report holds before starting a check.… - `tower_load_template` (writes): Set up Overwing Tower for this organization by loading the starter workflow: email purchase order to order entry, with create_order, update_order and… - `tower_create_agent` (writes): Create a scoped agent identity and its key. Needs an organization key. Scope it to the operations the agent needs (for example create_order) rather than *… - `tower_list_agents` (read-only): List this organization's Tower agents with scopes, status and last use. Keys are never returned. Needs an organization key. - `tower_revoke_agent` (writes): Revoke an agent. Its key stops working at once and cannot be restored. Needs an organization key. - `tower_capabilities` (read-only): List the operations this agent is allowed to call, each with the JSON Schema its input must match and its compensating operation. Call this first; build inputs… - `tower_decide` (read-only): Ask Tower how it would rule on an operation without doing anything: auto (would execute), review (a person must approve), or reject. Returns the score, the… - `tower_submit_action` (writes): Ask Tower to perform an operation on the legacy system. Tower decides: executed (done), pending (a person must approve; poll tower_get_action, do not… - `tower_get_action` (read-only): Status and result of an action: pending, approved, executed, failed, compensated, or rejected. Use it to poll an action that is waiting on human review. Needs… - `tower_compensate` (writes): Run the compensating operation for an executed action, for example cancel the order that create_order made. Runs once; repeating it returns the first outcome.… - `tower_get_receipt` (read-only): Fetch one signed receipt by id or by sequence number: the payload, its hash, the previous link's hash, and the Ed25519 signature. Needs an agent key. - `tower_verify_receipts` (read-only): Recompute every hash and check every signature over a range of this organization's receipts. Reports the first break, if any. Defaults to the whole chain (up… - How its tools read to an agent (0 errors, 12 warnings, 1 note, about 6,650 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score): - warn TC11 atlas_agents: 2 parameters without a description: limit, operator - warn TC11 atlas_register_agent: 3 parameters without a description: description, follows_robots_txt, purpose - warn TC11 create_rule_set: none of its 4 parameters has a description - warn TC11 evaluate_batch: none of its 4 parameters has a description - warn TC11 get_evaluation: its one parameter, id, has no description - warn TC11 get_rule_set: its one parameter, slug, has no description - warn TC11 get_usage: its one parameter, days, has no description - warn TC11 list_evaluations: none of its 4 parameters has a description - warn TC11 list_rule_sets: its one parameter, include_inactive, has no description - warn TC11 tower_decide: 1 parameter without a description: operation - warn TC11 tower_submit_action: 2 parameters without a description: dry_run, operation - warn TC11 tower_verify_receipts: none of its 2 parameters has a description - note TC24 server: 34 of 34 tools have no outputSchema - JSON: https://www.anchorterminal.com/api/v1/tools/overwing-mcp.json - Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming