fip-mcp

check

Validate a local folder or Zenodo record/DOI against a community's FAIR Implementation Profile to return deterministic pass, fail, or manual verdicts for each declared resource.

Instructions

Check a folder or a Zenodo record against the community's FIP.

target: a local folder path, a Zenodo record URL or id, or a Zenodo DOI.

The verdicts are deterministic: each declared resource is matched to a probe of facts read from the target (DOIs, licence, repository, file formats, RO-Crate). Statuses: pass, fail (with fix), manual (no automatic probe — ask the user, do not guess), no-choice (the community left it open), planned-only. offProfileFormats lists data formats present in the target that the community did not declare. Report results as given; do not upgrade a manual to pass.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "community": "<community>",
      "target": "<target>"
    },
    "name": "check"
  }
}

Input Schema

Name	Required	Description	Default
`target`	Yes
`community`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A3.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it states verdicts are deterministic, enumerates the status taxonomy (pass, fail with `fix`, manual, no-choice, planned-only), and exposes `offProfileFormats`. It does not state whether the target is mutated or only read, nor any auth or rate-limit behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the one-line purpose, then parameter detail, then the verdict taxonomy and reporting rule. Dense but every block adds information; no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description usefully documents statuses and `offProfileFormats`, and it warns against upgrading `manual` to `pass`. It still omits the meaning/format of the required `community` argument and any statement about side effects, leaving a gap for a two-required-param validation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It fully specifies `target` (local folder path, Zenodo record URL or id, or DOI) but leaves `community` unexplained — no format, no pointer to how a community id is obtained, despite it being required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: check a folder or Zenodo record against the community's FIP (profile). An agent can tell this is a validation tool rather than a lookup, though it never names which sibling (e.g. profile or recommend) to use instead.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the validation framing and by the instruction to ask the user on `manual` verdicts rather than guess, but there is no explicit when-to-use/when-not guidance and no named alternative among communities, crosswalk, profile, recommend.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server