Schema | mcp-tools

mcp-tools

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCPTOOLS_DB`	No	Path to a SQLite file to persist the results of grade_answer and model_drift. Unset, nothing is written and the server behaves exactly as before.
`MCPTOOLS_CORPUS`	No	Path to a notes.json corpus file (a {"id": "text", ...} file) used by the search tool. Set to point search at your own notes.

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }

Functions exposed to the LLM to take actions

Name	Description
calcA	Evaluate an arithmetic expression safely (no code execution; names, calls and imports are rejected).
searchA	BM25 keyword search over a small bundled document corpus; returns the top matches with their scores.
grade_answerA	Check a draft answer against its sources and report which sentences the sources do NOT support — fabricated figures and claims the sources never make. Deterministic and lexical, not a model judgement. Call this on your own answer before giving it to the user when the answer is supposed to be grounded in provided material.
model_driftA	Look up how a live LLM is currently scoring on a public, frozen eval suite (accuracy, latency, answer length, reliability, refusal rate) and whether those moved since the previous weekly run. Use it to check whether a model you're about to rely on has quietly changed. Omit `model` to list every tracked model.
compare_runsA	Ask whether a project's most recent stored eval run regressed against the one before it — per-case, so a better average can't hide a case that broke.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/egnaro9/mcp-tools'

If you have feedback or need assistance with the MCP directory API, please join our Discord server