| FMRS | 65 / 100 · C | 75 / 100 · B | 73 / 100 · B |
|---|
| Reliability | 9 / 20 | 13 / 20 | 12 / 20 |
|---|
| Security and permissions | 13 / 20 | 12 / 20 | 13 / 20 |
|---|
| Maintenance | 13 / 20 | 16 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 17 / 20 | 16 / 20 |
|---|
| Setup experience | 14 / 20 | 17 / 20 | 16 / 20 |
|---|
| Best for | - Researchers and biomedical agents needing programmatic PubMed or Europe PMC access
- Workflows requiring structured literature metadata, full text, and citation output
- Literature-management tasks involving DOI, PMID, and PMCID identifiers
| - Scenarios needing clean, structured web context fed to an AI assistant
- Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
| - Q&A and research scenarios that need real-time, clean web content
- Users with an existing Exa account who want a zero-deployment remote option
|
|---|
| Not for | - Users seeking searches across non-biomedical databases
- Workflows requiring guaranteed full-text availability for every article
- Users that need this server to be treated as an official PubMed or NCBI server
| - Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
- Sites that explicitly disallow automated access (robots.txt)
| - Scenarios requiring a strict allowlist of search sources that can't use a third-party search service
- Budget-sensitive, high-volume search scenarios (remote/API calls may incur cost)
|
|---|
| Required permissions | - The server needs access to NCBI services; Europe PMC access is needed when Europe PMC features are enabled.
- Full-text fallback through Unpaywall requires UNPAYWALL_EMAIL and access to Unpaywall.
- API keys and contact emails are optional; NCBI_API_KEY can increase the NCBI rate limit.
- Streamable HTTP deployments can use none, jwt, or oauth authentication; the default is none.
| - Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
- firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
| - Requires an Exa API key for full functionality; OAuth login is optional in remote mode
- web_fetch_exa retrieves content from a specified URL; agent_run performs multi-step autonomous actions and needs the user to have clear expectations of Agent behavior
|
|---|
| Risks and side effects | - Full-text retrieval depends on PMC, Europe PMC, or legal open-access sources and may return unavailable or truncated results.
- Unpaywall results may include best-effort warnings and may be returned as HTML Markdown or PDF text.
- The source does not provide further details about authentication or availability of the public hosted instance.
- NCBI and Europe PMC requests are affected by rate limits, timeouts, and retry settings.
| - Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
- firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
| - The API key should be stored carefully — avoid leaving it in plaintext in client config files on untrusted machines
- agent_run is a multi-step autonomous tool with a longer action chain — try it on low-risk tasks first
|
|---|
| Supported clients | Claude Desktop, Cursor, VS Code | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp | Claude Desktop, Claude Code, VS Code, Cursor, Windsurf, Zed, Amp, Kiro, LM Studio, Antigravity |
|---|
| Tools | 11 | 11 | 4 |
|---|