| FMRS | 55 / 100 · C | 77 / 100 · B | 75 / 100 · B |
|---|
| Reliability | 8 / 20 | 12 / 20 | 13 / 20 |
|---|
| Security and permissions | 12 / 20 | 16 / 20 | 12 / 20 |
|---|
| Maintenance | 10 / 20 | 16 / 20 | 16 / 20 |
|---|
| Documentation | 14 / 20 | 18 / 20 | 17 / 20 |
|---|
| Setup experience | 11 / 20 | 15 / 20 | 17 / 20 |
|---|
| Best for | - Math-paper readers who need a strict separation between evidence and guesses
- Researchers who want an AI agent to help map theorems and dependencies inside a local workspace
- People who want reading artifacts as Markdown they can keep in Git or notes
- Users who want to review external references before importing them
| - Hevy PRO users who want AI assistants to directly access their workout data
- People who prefer using MCP clients like Claude, Cursor, Codex for fitness tracking
- Anyone needing summaries and insights from their training data
| - 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
|
|---|
| Not for | - People expecting the tool to prove or verify mathematical correctness
- Anyone wanting automatic infinite crawling of the citation chain (A cites B, B cites C)
- Users needing semantic theorem matching or equivalence judgments for similarly worded results
- Users with scanned or OCR-heavy PDFs where extraction may be sparse
- Users who expect a full TeX engine for complex projects
| - Users without a Hevy PRO subscription (API key required)
- Users who want to use the server without an API key
- Those needing delete workflows (Hevy API does not expose delete endpoints)
| - 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)
|
|---|
| Required permissions | - Read and write SQLite workspace files at user-chosen local paths
- Read user-supplied local LaTeX projects and local PDF files
- Download e-prints from arXiv's fixed e-print endpoint
- Query public metadata services (Crossref, OpenAlex, arXiv) when the user runs a reference search
- Write generated Markdown reports and manifest files into a user-specified artifact directory
| - Requires HEVY_API_KEY environment variable for Hevy API authentication
- Can create, update, and replace workouts, routines, folders, templates, and body measurements via tools
- Read operations can fetch workouts, routines, folders, templates, history, and user info
| - 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
|
|---|
| Risks and side effects | - The workspace stores text, source spans, and proof evidence extracted from papers, so committing databases or private manuscripts can leak content
- The Scholarly Reference Resolver only searches public metadata and stops with explicit boundaries for ambiguous, old, paywalled, or metadata-only literature, requiring manual sourcing
- An empty dependency result only means no resolvable theorem-label references were found under the current rule; it is not evidence that the theorem has no mathematical dependencies
- Scanned PDFs may yield sparse text and missing evidence
- The parser is not a full TeX engine, so complex projects may need an explicit main_file
| - API key can be misused if leaked; do not expose in URLs, logs, or screenshots
- Create operations may produce duplicates on retry; update operations replace existing records
- The server sends data to the Hevy API and may send telemetry to external services unless disabled
| - 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
|
|---|
| Supported clients | MCP clients accepting JSON-style stdio configuration | Claude Desktop, Cursor, Codex, Google Antigravity | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp |
|---|
| Tools | 54 | 26 | 11 |
|---|