Firecrawl MCP Server

Firecrawl inspect research paper

firecrawl_research_inspect_paper

Read-only

Retrieve canonical metadata for a single paper ID (arXiv, PMC, PMID, or DOI). Returns title, abstract, authors, categories, source IDs, and dates as markdown for citation and review.

Instructions

Retrieve canonical metadata for one paper ID, such as an arXiv, PMC, PMID, or DOI identifier. Returns the title, abstract, authors, categories, source IDs, and dates as 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": {
      "paperId": "<paperId>"
    },
    "name": "firecrawl_research_inspect_paper"
  }
}

Input Schema

Name	Required	Description	Default
`paperId`	Yes	Canonical paperId or primaryId such as `arxiv:1706.03762`, `pmcid:PMC12530322`, `pmid:40953549`, or `doi:10.1016/j.neunet.2025.108095`.

Output Schema

Name	Required	Description	Default
`paper`	No	Canonical metadata for the requested paper, absent when it was not found.
`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

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds that the response is metadata-only (title, abstract, authors, categories, source IDs, dates) rendered as markdown, but says nothing about behavior on unknown or malformed IDs, and the output schema already defines the return shape.

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?

Two sentences, zero filler: the action and scope come first, the return fields second. Nothing is repeated or padded.

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 single-parameter read tool with annotations and an output schema, the definition covers purpose, accepted ID forms, and response content. Only edge-case behavior (not-found or invalid identifier) is absent, which is a minor gap.

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 the paperId property already documents the arxiv:/pmcid:/pmid:/doi: prefix conventions with examples. The description restates the same identifier families without adding format rules, constraints, or fallback behavior, so it adds little beyond the schema.

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 ('Retrieve canonical metadata') and resource ('one paper ID'), and enumerates the identifier schemes accepted. It implicitly separates itself from firecrawl_research_read_paper by emphasizing metadata rather than content, but it never names that sibling explicitly.

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

Usage Guidelines3/5

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

Usage is only implied: an agent can infer this is the lookup-by-ID path, but the description never says when to prefer it over firecrawl_research_search_papers (find by query) or firecrawl_research_read_paper (fetch full text). No exclusions or prerequisites are given.

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