| FMRS | 69 / 100 · C | 77 / 100 · B | 75 / 100 · B |
|---|
| Reliability | 11 / 20 | 12 / 20 | 13 / 20 |
|---|
| Security and permissions | 13 / 20 | 16 / 20 | 12 / 20 |
|---|
| Maintenance | 15 / 20 | 16 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 18 / 20 | 17 / 20 |
|---|
| Setup experience | 14 / 20 | 15 / 20 | 17 / 20 |
|---|
| Best for | - Researchers, students, and academics who want to integrate their Zotero library with AI assistants.
- Users who need quick retrieval, summarization, and annotation of papers.
- Those looking for semantic search to discover related research.
- Users who want to automate library management tasks like bulk adding and deduplication.
| - 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 | - Users who don't need AI integration and just want a terminal interface (use zotero-cli).
- Users who don't use Zotero.
- Users who require fully offline operation without local Zotero installation (web API mode still needs internet).
| - 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 | - Reads local Zotero database files (default path).
- Writes to Zotero via Web API in hybrid mode (add, update, delete items).
- Accesses Zotero attachment files (e.g., PDFs) to extract full text and annotations.
- When semantic search is enabled, calls embedding model APIs (e.g., OpenAI, Gemini) and stores index data.
- When scite tools are enabled, calls scite.ai public API.
| - 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 | - AI assistants may misinterpret or misread library data; verify important information manually.
- Web API mode requires a Zotero API key; if compromised, unauthorized access to your library is possible.
- Semantic search indexes may contain sensitive content; protect stored embeddings.
- Enabled optional tool groups (e.g., scite) trigger external network requests.
| - 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 | Claude Desktop, Claude Code, ChatGPT, Cherry Studio | Claude Desktop, Cursor, Codex, Google Antigravity | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp |
|---|
| Tools | 37 | 26 | 11 |
|---|