Firecrawl MCP Server

Firecrawl developer search

firecrawl_developer_search

Read-only

Search public repositories, GitHub issues, merged pull requests, READMEs, and code documentation to answer programming questions with ranked source evidence and matched passages.

Instructions

Search an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and code documentation for programming questions that need external documentation or upstream evidence.

Returns ranked results with an ID, source type, URL, title, and the matched passages in markdown.

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": "firecrawl_developer_search"
  }
}

Input Schema

Name	Required	Description
`k`	No	Number of ranked results to return (default 10).
`query`	Yes	Natural-language developer question or search phrase, including the library, error message, or API involved when relevant.
`skills`	No	Set to "only" to search only agent-skill files.

Output Schema

Name	Required	Description	Default
`results`	Yes	Ranked results, in the order the text block lists them.
`agent_hints`	No	Optional response guidance from the Firecrawl API.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.28.2Nov 4, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that by enumerating which corpora are indexed and stating that results are ranked, which matters for judging coverage of a search. It does not mention result limits, rate limits, or auth, and the return-shape sentence largely duplicates the output schema.

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?

Two sentences, front-loaded with the scope of the index before the return format; nothing is padded. The second sentence's list of returned fields is partly redundant given an output schema exists, which keeps it from a 5.

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 search tool with full schema coverage, annotations, and an output schema, the description covers purpose, corpus scope, and ranking. The main remaining gap is routing guidance against the sibling general-purpose search and scrape tools, which the agent must infer from the word 'developer'.

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 description coverage is 100%, so all three parameters (query, k, skills) are already documented in the schema, including the k default and the 'only' enum for skills. The description adds no further meaning about how to phrase the query, how ranking is affected by k, or what agent-skill files are. Baseline 3 applies when the schema carries the parameter burden.

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 a well-defined resource: an index of public repositories, GitHub issues, merged PRs, READMEs, and code documentation, scoped to programming questions. The developer-focused scope implicitly separates it from the general web search sibling, but no sibling is named explicitly, so the differentiation is inferred rather than stated.

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 a clear use condition — programming questions that need external documentation or upstream evidence — which tells the agent what kind of task this tool serves. It stops short of naming alternatives such as firecrawl_search or firecrawl_scrape, or stating when not to use it, so routing between the two search tools still requires inference.

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