Skip to main content
Glama
Sign In

CrawlCheck

by io.github.emmanuelorta
OverviewDiscussionsAdmin

Pre-release check for an MCP server

mcp_precheck
Read-onlyIdempotent

For MCP server publishers, before releasing a new version. Give the server name (as listed in the MCP Registry) or its endpoint, the new tools/list result and the new serverInfo.version; with no tools the endpoint is read as it serves now. Returns, against CrawlCheck's last read of that server, what public change logs will record: tools added and removed, descriptions rewritten, input schemas widened, annotations changed (read-only to write and non-destructive to destructive flagged as escalations), whether the version moved, and verdicts such as version_bump_needed or looks_like_rug_pull_risk. Signed. No tool on the checked server is called.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "mcp_precheck"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolsNoThe new tools/list tools array; omit to read the endpoint live
versionNoThe new serverInfo.version
endpointNoRemote MCP endpoint URL, e.g. https://mcp.example.com/mcp
server_nameNoName in the MCP Registry, e.g. io.github.owner/server

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent annotations: it discloses the comparison baseline (CrawlCheck's last read), that no tool on the checked server is invoked, that results are signed, and specifically that read-only→write and non-destructive→destructive transitions are flagged as escalations. The verdict vocabulary is also surfaced.

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?

Purpose and audience are front-loaded and every clause carries information about inputs, comparison baseline, or output. It is dense and reads as a long run-on, which slightly hurts scannability, but there is no filler.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does so: it enumerates what the diff records (added/removed tools, rewritten descriptions, widened schemas, annotation escalations, version movement) and names verdict types. Combined with the safety statement, an agent has enough to call it correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds conditional meaning the schema lacks: omitting tools causes the endpoint to be read as it currently serves, and server_name is tied to MCP Registry naming. It also frames version as the new serverInfo.version, clarifying what is being compared.

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

Purpose5/5

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

States a specific verb and resource: a pre-release diff of a new tools/list plus serverInfo.version against CrawlCheck's last read of that server. It names the audience (MCP server publishers) and the exact artifact produced (public change log entries and verdicts), which distinguishes it from registry lookup or site-scanning siblings.

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

Usage Guidelines4/5

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

Gives clear timing ('before releasing a new version') and the two ways to identify the target (registry name or endpoint), plus the case where tools are omitted. It does not name sibling alternatives such as mcp_servers or preflight, so the when-not-to-use boundary is left implicit.

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

All CrawlCheck toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources