Fetch (MCP reference server) by MCP project (reference servers)

# Fix list: Fetch (MCP reference server)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/fetch-reference-server, the October 2026 research run, assessed 1 October 2026. Grade C, 57.6 out of 100.

This 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.

For a coding agent working on Fetch (MCP reference 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.

## 1. Security & auth, 30 out of 100, up to 12.3 more on the total

Why it scored 30: No credentials to leak and nothing to scope, so the middle band (20). GET only, but it follows redirects and reaches private and loopback addresses with no allow list or block, which the README warns about. The only control is `--proxy-url` (5). It returns untrusted page text unmarked, and the README has no prompt-injection guidance (0). No call log (0). The repository's SECURITY.md says it isn't eligible for vulnerability reports. Advisories for the git server were still published in public, and none exist for fetch (5).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 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.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 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.
- 0 to 15, audit logs or per-call visibility for the operator.
- 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.

## 2. Reliability, 53 out of 100, up to 9.4 more on the total

Why it scored 53: Scored as a local stdio package. Official PyPI package mcp-server-fetch and the mcp/fetch Docker image, Python 3.10 or later stated (20). The monorepo's Python workflow runs pytest on every package with tests, and the fetch server has 20 tests since January 2026. We couldn't see whether the default branch passes, so 20 of 25. GitHub's robots rules blocked our issue search, so we scored crash handling from the history instead. A crash on malformed input was fixed in March 2026 (#3515) (8). Date versions such as 2026.8.18 with no per-package changelog. The MCP SDK 2.0 pin is called out in the README (5). The classifier says 4 - Beta and the repository calls its servers reference implementations, not production-ready (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 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.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 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.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 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.

## 3. Maintenance & community, 42 out of 100, up to 5.1 more on the total

Why it scored 42: 2026.8.18 on 18 August, 44 days ago (20). Two releases since 3 July, 2026.7.10 and 2026.8.18 (0). Fix pull requests for fetch merged in March and August 2026. We couldn't read the open issue list (12). Not in the official MCP registry, though the README carries an `mcp-name` for io.github.modelcontextprotocol/server-fetch (0). Dependency groups bumped for security alerts in June and July, and CI runs on push (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 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.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 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.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 4. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

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.
- 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.
- 20, a free tier or trial that doesn't need a card.
- 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.

## 5. Schema & documentation, 70 out of 100, up to 4.9 more on the total

Why it scored 70: The one tool takes a typed JSON Schema built from a Pydantic model (25). No llms.txt. The README is Markdown on GitHub (5). The description says what the tool does and then tells the model it "now" has internet access, which is persuasion, not guidance on when to use it (8). `url` is a URI, `max_length` an integer above 0 and below 1,000,000 with a default of 5,000, `start_index` 0 or more, `raw` a boolean (15). Configuration examples for several clients, and errors come back as MCP errors with readable messages (10). Dated PyPI versions and monorepo releases, with no changelog for this package (7).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 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.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 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.

## 6. Agent ergonomics, 78 out of 100, up to 3.6 more on the total

Why it scored 78: One tool, about 1,160 characters of definition, roughly 300 tokens (25). `max_length` and `start_index` page through long documents, and a truncated response names the next `start_index` (20). Invalid input returns INVALID_PARAMS, and a robots.txt refusal explains why and what the user can do (16). No annotations, so no `readOnlyHint`, though a GET is safe to repeat (5). Only `url` is required and the defaults are sensible. Python only, plus a Docker image (12).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 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).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 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.

## 7. Transparency & trust, 75 out of 100, up to 2.2 more on the total

Made of editorial 76, provenance 74.

Why it scored 75: The package is MIT, inside a repository moving new contributions to Apache-2.0, both OSI licences (28). Local software that keeps nothing and sends nothing beyond the request. There's no written statement, but the source is short and shows it (20). Archived servers moved to a separate repository, and the SDK 2.0 pin is documented, but there's no deprecation policy (8). No telemetry in the code (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 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.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: modelcontextprotocol.io, registered 2024-11-18 (1 year) (3 of 15)
- Status page: not found (0 of 10)

## What we couldn't check

What 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.

- unchecked: open issues and reply times for the fetch server (GitHub's robots rules blocked our issue search)
- unchecked: whether CI on the default branch currently passes
- Why the README's `mcp-name` for io.github.modelcontextprotocol/server-fetch has no entry in the official registry

## Weaknesses

- Reaches private and loopback addresses and follows redirects, with no allow list
- SECURITY.md says the repository isn't eligible for vulnerability reports
- Classed 4 - Beta and described as not production-ready
- Two releases since July and no entry in the official MCP registry
- No JavaScript rendering and no untrusted-content marking

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Fetch with the 5,000-character default and continue from the `start_index` the truncation note gives
- Expect empty bodies from JavaScript-rendered sites and switch to a browser tool
- Treat a robots.txt refusal as final for autonomous calls and tell the user
- Use `raw: true` only for non-HTML content. It skips the Markdown conversion and returns the page as served

## What the review panel asked for

- when-not guidance
- a rendering option

## When it's done

Send 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.