Lazaretto

Find an MCP server for a job (free)

find_mcp_servers

Read-onlyIdempotent

Find an MCP server for a job, free and with no key: describe what you need ("postgres", "send slack messages", "browser automation") and get matching servers from the official MCP registry, each with its endpoint, the command to add it to Claude Code, its tools, and what Lazaretto's latest read found. Only servers whose tools we read with nothing matching our tool-poisoning rules, or live servers that ask you to sign in before listing tools (said plainly), are returned; servers we flagged or could not reach are left out. Remote servers only: for a local stdio server, check its tool list with check_mcp_tools. Use it whenever you need a capability you do not have yet.

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": {
      "query": "<query>"
    },
    "name": "find_mcp_servers"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	How many servers to return (default 5).
`query`	Yes	What the server should do, or its name: "github issues", "notion", "web scraping".

Output Schema

Name	Required	Description	Default
`note`	No
`servers`	No
`query_terms`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 30, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare this is a safe, read-only, idempotent operation, but the description adds critical behavioral context beyond them: only servers with tools cleared by the poisoning rules or live sign-in-gated servers are returned; flagged or unreachable servers are omitted. This is exactly the kind of filtering and scope disclosure the agent needs to interpret results correctly.

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?

The purpose and scope are front-loaded, and every sentence contributes useful filtering or routing information. The single paragraph is dense and a bit long, but there is no filler or repeated content.

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?

Given an output schema, full parameter coverage, and annotations, the description supplies the remaining context an agent needs: remote-only scope, poisoning-rule filtering, sign-in-gated behavior, and where to go for local stdio servers. Nothing material is missing.

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 100% and both parameters are described in the schema, including the limit range and default. The description reinforces the query with examples ('postgres', 'send slack messages', 'browser automation'), but does not add syntax or format details beyond what the schema already provides. Baseline 3 is correct when the schema does the heavy lifting.

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?

Opens with a specific verb and resource ('Find an MCP server for a job') and immediately scopes it: official MCP registry, remote servers only, each result includes endpoint, Claude Code install command, tools, and latest read status. It also names the sibling it is not (check_mcp_tools for local stdio servers), so the agent can separate it from alternatives without opening either schema.

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

Usage Guidelines5/5

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

States the trigger explicitly ('Use it whenever you need a capability you do not have yet') and gives the exclusion/alternative: 'for a local stdio server, check its tool list with check_mcp_tools.' The filtering rules for poisoning-flagged or unreachable servers are also spelled out, so the agent knows what to expect before calling.

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

All Lazaretto tools Inspect

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.