{
  "fixes": {
    "slug": "salesforce-dx-mcp",
    "name": "Salesforce DX MCP Server",
    "listing": "https://www.anchorterminal.com/tools/salesforce-dx-mcp",
    "markdown": "# Fix list: Salesforce DX MCP Server\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/salesforce-dx-mcp, the October 2026 research run, assessed 1 October 2026. Grade C, 59.7 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Salesforce DX MCP Server: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Agent ergonomics, 53 out of 100, up to 7.6 more on the total\n\nWhy it scored 53: 88 tools across 15 toolsets in the README. Salesforce's own README warns that enabling all of them can overwhelm the context (5). Toolsets, `--tools`, an experimental `--dynamic-tools` mode and NON-GA tools off by default add back 10. `run_soql_query` has no row limit, and an open issue says large queries loop. `query_code_analyzer_results` has top-N and filters (8). Errors come back as `isError` results with readable text (14). 21 of the 38 tools defined in this repository set `readOnlyHint` or `destructiveHint`. `deploy_metadata` and `retrieve_metadata` are marked destructive, `delete_org` has an empty annotations object, and the ten `DevOps Center` tools have none. We couldn't read the LWC and Aura expert tools, which ship from separate packages (8). `--orgs` is required at start, and most tools require `usernameOrAlias` and an absolute `directory` on every call. Node only (8).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 2. Security \u0026 auth, 57 out of 100, up to 7.5 more on the total\n\nWhy it scored 57: Tools reuse the Salesforce CLI's encrypted OAuth or JWT auth files and pass usernames, never tokens. Tokens are revocable in the org, and access is bounded by the user's profile and permission sets (25). `--orgs` allow-lists which orgs the server can touch, toolsets limit what it can do and NON-GA tools are off by default. There's no read-only mode, `ALLOW_ALL_ORGS` exists, `DEFAULT_TARGET_ORG` re-resolves on every call, and deleting an org relies on the description asking the agent to confirm (12). SOQL results can carry user-entered record text, with no injection guidance (5). Org-side audit trails exist, but the MCP docs don't mention them. Local logs need `--debug` (5). SECURITY.md points to sfdc.co/SubmitVuln. No advisories published, and no security.txt per the 30 September check (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 3. Reliability, 65 out of 100, up to 7 more on the total\n\nWhy it scored 65: Scored as a local stdio package. Official npm package @salesforce/mcp, Node 20 or later stated (20). Unit tests on Linux and Windows and end-to-end tests run on every push to a branch, across 108 test files. We couldn't see whether the default branch passes (20). Issues moved to forcedotcom/mcp, which has 10 open. Five bugs from June and July 2025 are still open, and four 2026 reports (a `retrieve_metadata` race condition among them) are labelled investigating (12). Conventional-commit changelogs per package, but 0.30.13 and 0.30.14 have empty entries, the root CHANGELOG stops at 0.17.1 (August 2025), and tool renames in September and October 2025 shipped as bug fixes (8). Still 0.30.x. Individual tools are labelled GA or NON-GA, which counts for something (5).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 4. Maintenance \u0026 community, 36 out of 100, up to 5.6 more on the total\n\nWhy it scored 36: 0.30.15 on 9 July 2026, 84 days before the run date (20). One release since 3 July (0). Three commits since then, the last on 23 September. Issues moved to forcedotcom/mcp, where 2026 reports get an investigating label and 2025 bugs sit open (10). Not in the official MCP registry and no `mcpName` in package.json (0). CI runs on branches. The published 0.30.15 depends on mcp-provider-dx-core 0.9.8 although 0.10.0 was tagged on 21 May 2026 (6).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 5. Payments \u0026 pricing, 60 out of 100, up to 5 more on the total\n\nWhy it scored 60: Free, Apache-2.0, self-hosted, so 20 + 20 + 20. No payment protocol (0). The server needs a Salesforce org, and even a free Developer Edition needs a person to sign up and run `sf org login web` once.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 6. Schema \u0026 documentation, 70 out of 100, up to 4.9 more on the total\n\nWhy it scored 70: Every in-repository tool takes a Zod schema published as JSON Schema (25). No llms.txt. The README and the developer.salesforce.com page are the docs (5). Shared parameters carry agent instructions (\"NEVER guess or make-up a username or alias\", \"run #get_username\") and `delete_org` tells the agent to confirm with the user. Many descriptions are one line (`run_soql_query` says only \"Run a SOQL query against a Salesforce org\") (12). Mostly strings, with required fields marked and absolute-path validation for `directory`. Few enums (10). Configuration examples for several clients. Errors return `isError` with a message. No documented error list (8). Semver 0.x with generated per-package changelogs, several entries empty (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 7. Transparency \u0026 trust, 69 out of 100, up to 2.7 more on the total\n\nMade of editorial 61, provenance 76.\n\nWhy it scored 69: Apache-2.0 for the repository. The LWC and Aura expert providers ship as separate npm packages whose source isn't in this repository (25). The server runs locally and reads CLI auth files. Telemetry sends tool name, runtime, error flag and response size. There's no MCP-specific data statement beyond Salesforce's general privacy policy (15). NON-GA labels mark what may change, but renames in 2025 came with no deprecation notice (5). Telemetry is on by default, disclosed in the README and switched off with `--no-telemetry`. The source also names an upload endpoint for metrics that the README doesn't mention (16).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Status page: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: whether CI on the default branch passes (the test workflow ignores pushes to main)\n- unchecked: the source and licence of @salesforce/mcp-provider-lwc-experts and -aura-experts, and their tool definitions and annotations\n- Why the published 0.30.15 pins provider versions older than tags already in the repository\n- What the telemetry upload endpoint named in the source receives and how long Salesforce keeps it\n\n## Weaknesses\n\n- 88 tools; Salesforce's README warns that enabling all of them overwhelms the context\n- Ten `DevOps Center` tools and `delete_org` carry no annotations\n- One release (0.30.15, 9 July 2026) in the last 90 days, and 2025 bug reports still open\n- Not in the official MCP registry\n- `run_soql_query` has no row limit, and an open issue reports loops on large datasets\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Start with `--toolsets orgs,metadata,data` and add `testing` or `devops` only when the task needs them\n- Pass explicit aliases to `--orgs`; `DEFAULT_TARGET_ORG` follows whatever the default org is in the working directory at call time\n- Call `get_username` before any org tool instead of guessing `usernameOrAlias`, and send `directory` as an absolute path\n- Put `LIMIT` in every SOQL query; the tool doesn't cap rows\n- For business records like contacts or opportunities this is the wrong server; use the platform APIs behind an integration user\n\n## What the review panel asked for\n\n- annotate delete_org and the `DevOps Center` tools\n- document row limits on run_soql_query\n- read-only toolset mode\n- annotations on `DevOps Center` tools\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "C",
    "score": 59.7,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 53,
        "maxGain": 7.6,
        "reason": "88 tools across 15 toolsets in the README. Salesforce's own README warns that enabling all of them can overwhelm the context (5). Toolsets, `--tools`, an experimental `--dynamic-tools` mode and NON-GA tools off by default add back 10. `run_soql_query` has no row limit, and an open issue says large queries loop. `query_code_analyzer_results` has top-N and filters (8). Errors come back as `isError` results with readable text (14). 21 of the 38 tools defined in this repository set `readOnlyHint` or `destructiveHint`. `deploy_metadata` and `retrieve_metadata` are marked destructive, `delete_org` has an empty annotations object, and the ten `DevOps Center` tools have none. We couldn't read the LWC and Aura expert tools, which ship from separate packages (8). `--orgs` is required at start, and most tools require `usernameOrAlias` and an absolute `directory` on every call. Node only (8).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 57,
        "maxGain": 7.5,
        "reason": "Tools reuse the Salesforce CLI's encrypted OAuth or JWT auth files and pass usernames, never tokens. Tokens are revocable in the org, and access is bounded by the user's profile and permission sets (25). `--orgs` allow-lists which orgs the server can touch, toolsets limit what it can do and NON-GA tools are off by default. There's no read-only mode, `ALLOW_ALL_ORGS` exists, `DEFAULT_TARGET_ORG` re-resolves on every call, and deleting an org relies on the description asking the agent to confirm (12). SOQL results can carry user-entered record text, with no injection guidance (5). Org-side audit trails exist, but the MCP docs don't mention them. Local logs need `--debug` (5). SECURITY.md points to sfdc.co/SubmitVuln. No advisories published, and no security.txt per the 30 September check (10).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 65,
        "maxGain": 7,
        "reason": "Scored as a local stdio package. Official npm package @salesforce/mcp, Node 20 or later stated (20). Unit tests on Linux and Windows and end-to-end tests run on every push to a branch, across 108 test files. We couldn't see whether the default branch passes (20). Issues moved to forcedotcom/mcp, which has 10 open. Five bugs from June and July 2025 are still open, and four 2026 reports (a `retrieve_metadata` race condition among them) are labelled investigating (12). Conventional-commit changelogs per package, but 0.30.13 and 0.30.14 have empty entries, the root CHANGELOG stops at 0.17.1 (August 2025), and tool renames in September and October 2025 shipped as bug fixes (8). Still 0.30.x. Individual tools are labelled GA or NON-GA, which counts for something (5).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 36,
        "maxGain": 5.6,
        "reason": "0.30.15 on 9 July 2026, 84 days before the run date (20). One release since 3 July (0). Three commits since then, the last on 23 September. Issues moved to forcedotcom/mcp, where 2026 reports get an investigating label and 2025 bugs sit open (10). Not in the official MCP registry and no `mcpName` in package.json (0). CI runs on branches. The published 0.30.15 depends on mcp-provider-dx-core 0.9.8 although 0.10.0 was tagged on 21 May 2026 (6).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 60,
        "maxGain": 5,
        "reason": "Free, Apache-2.0, self-hosted, so 20 + 20 + 20. No payment protocol (0). The server needs a Salesforce org, and even a free Developer Edition needs a person to sign up and run `sf org login web` once.",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 70,
        "maxGain": 4.9,
        "reason": "Every in-repository tool takes a Zod schema published as JSON Schema (25). No llms.txt. The README and the developer.salesforce.com page are the docs (5). Shared parameters carry agent instructions (\"NEVER guess or make-up a username or alias\", \"run #get_username\") and `delete_org` tells the agent to confirm with the user. Many descriptions are one line (`run_soql_query` says only \"Run a SOQL query against a Salesforce org\") (12). Mostly strings, with required fields marked and absolute-path validation for `directory`. Few enums (10). Configuration examples for several clients. Errors return `isError` with a message. No documented error list (8). Semver 0.x with generated per-package changelogs, several entries empty (10).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 69,
        "maxGain": 2.7,
        "reason": "Apache-2.0 for the repository. The LWC and Aura expert providers ship as separate npm packages whose source isn't in this repository (25). The server runs locally and reads CLI auth files. Telemetry sends tool name, runtime, error flag and response size. There's no MCP-specific data statement beyond Salesforce's general privacy policy (15). NON-GA labels mark what may change, but renames in 2025 came with no deprecation notice (5). Telemetry is on by default, disclosed in the README and switched off with `--no-telemetry`. The source also names an upload endpoint for metrics that the README doesn't mention (16).",
        "blend": "editorial 61, provenance 76",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: whether CI on the default branch passes (the test workflow ignores pushes to main)",
      "unchecked: the source and licence of @salesforce/mcp-provider-lwc-experts and -aura-experts, and their tool definitions and annotations",
      "Why the published 0.30.15 pins provider versions older than tags already in the repository",
      "What the telemetry upload endpoint named in the source receives and how long Salesforce keeps it"
    ],
    "weaknesses": [
      "88 tools; Salesforce's README warns that enabling all of them overwhelms the context",
      "Ten `DevOps Center` tools and `delete_org` carry no annotations",
      "One release (0.30.15, 9 July 2026) in the last 90 days, and 2025 bug reports still open",
      "Not in the official MCP registry",
      "`run_soql_query` has no row limit, and an open issue reports loops on large datasets"
    ],
    "agentNotes": [
      "Start with `--toolsets orgs,metadata,data` and add `testing` or `devops` only when the task needs them",
      "Pass explicit aliases to `--orgs`; `DEFAULT_TARGET_ORG` follows whatever the default org is in the working directory at call time",
      "Call `get_username` before any org tool instead of guessing `usernameOrAlias`, and send `directory` as an absolute path",
      "Put `LIMIT` in every SOQL query; the tool doesn't cap rows",
      "For business records like contacts or opportunities this is the wrong server; use the platform APIs behind an integration user"
    ],
    "requests": [
      {
        "text": "annotate delete_org and the `DevOps Center` tools",
        "reviews": 1
      },
      {
        "text": "document row limits on run_soql_query",
        "reviews": 1
      },
      {
        "text": "read-only toolset mode",
        "reviews": 1
      },
      {
        "text": "annotations on `DevOps Center` tools",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "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"
  }
}