Skip to main content
Glama
Sign In
TrustedMCP

TrustedMCP

by akshay-bhanderi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Check an MCP config

check_config
Read-onlyIdempotent

Grade every MCP server in a client config to surface checks and fixes, reading local files or supplied JSON without sending credentials or paths off your machine.

Instructions

Grade every MCP server in an MCP config. With no arguments, reads the usual config files on this machine (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf). Or pass client for one app, path for one file, or config with the JSON text. The file is read locally; only package names, image names and server URLs (no query strings) are sent to TrustedMCP. Env vars, headers, tokens and file paths never leave the machine.

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": "check_config"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoPath to one .json or .jsonc MCP config file
clientNoOnly this app: claude_desktop, claude_code, cursor, vscode or windsurf
configNoThe config JSON itself, e.g. the contents of claude_desktop_config.json

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/openWorld/idempotent/destructive annotations, it discloses exactly which local files are discovered and, critically, what data is transmitted off-machine (package names, image names, server URLs with query strings stripped) versus what is never sent (env vars, headers, tokens, file paths). That privacy contract is the behavior an agent most needs before invoking a tool that phones home.

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

Conciseness5/5

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

Three sentences, front-loaded with the purpose, then the invocation modes, then the data-handling caveat. Every clause carries information; nothing is padding or restated from the schema.

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

Completeness4/5

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

For a read-only, zero-required-parameter tool with no output schema, it covers purpose, modes and privacy adequately. It does not say what a 'grade' looks like in the response (score, findings, severity), so an agent knows how to call it but not quite what it will get back.

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 already 100%, so the baseline is 3; the description adds real value by documenting the zero-argument default, which the schema cannot express, and by restating each parameter's role (one app, one file, raw JSON text). The `config` example of claude_desktop_config.json contents duplicates schema text and adds little.

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: 'Grade every MCP server in an MCP config.' That scope is distinct from the sibling tools (find_alternatives, lookup_server, registry_lookup), which look up or suggest servers rather than grading a whole config, so an agent can route correctly without opening a schema.

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 an explicit default behavior (no arguments reads the usual config files on this machine) and a per-argument mapping for the three selection modes: `client` for one app, `path` for one file, `config` for inline JSON. It never says when not to use it or points to a sibling, so it stops just short of a 5.

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

Deploy Server

Other Tools