FreeWeb-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FIRECRAWL_PORT | No | Fixed port; 0 selects an owned free port. | |
| FREEWEB_CONFIG | No | Configuration file path. | |
| EGO_BROWSER_BIN | No | ego-browser binary path. | |
| FREEWEB_DATA_DIR | No | Private Artifact/checkpoint directory (default ~/.freeweb-mcp). | |
| TINYFISH_API_KEY | No | TinyFish API key. | |
| FIRECRAWL_LOCAL_BIN | No | Firecrawl binary path. | |
| FREEWEB_EGO_UNRESTRICTED | No | Register the unrestricted browse_node tool. | |
| FREEWEB_FIRECRAWL_SEARCH_FALLBACK | No | Enable keyless Firecrawl Search fallback. | |
| FREEWEB_TINYFISH_FREE_ONLY_CONFIRMED | No | Set to true only after verifying the TinyFish account has no wallet spending capability. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchB | Search with TinyFish, optionally falling back once to keyless Firecrawl Search. TinyFish requires a free-only confirmed API key. |
| fetchC | Fetch 1-10 URLs. Firecrawl Local is preferred; only failed URLs may fall back to TinyFish when options are compatible. |
| mapB | Synchronously discover URLs from a sitemap and the starting page using Firecrawl Local. Map search is URL substring filtering, not semantic search. |
| crawlC | Start a bounded Firecrawl Local Crawl Job. Respect for robots.txt is mandatory. Returns immediately with a crawlId. |
| crawl_statusB | Read a Crawl Job checkpoint with page pagination. Lost jobs expose checkpoints but never imply resumable execution. |
| crawl_cancelA | Cancel an active Crawl Job and preserve its checkpoint. |
| browseC | Run managed TaskSpace lifecycle actions and allowlisted native Page methods. Can use an allowed user Profile. Not a network or operating-system sandbox. |
| browse_evaluateB | Execute arbitrary JavaScript in one ego-lite Page with one JSON argument. It can use website identity and change external state; it is not read-only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools have clearly distinct roles: search, fetch, map, and crawl target different web-access workflows. The main overlap is browse vs browse_evaluate, since both operate on a page and agents may need careful reading to know when to use managed page actions versus arbitrary JavaScript evaluation.
The set mixes simple verbs (search, fetch, map, crawl, browse) with compound names (browse_evaluate, crawl_status, crawl_cancel). The convention is readable but not consistent, especially the verb_verb browse_evaluate and crawl_* grouping.
Eight tools are well-scoped for a web search/fetch/crawl/browse server. Each tool has a plausible operational role, and the crawl lifecycle is split into start, status, and cancel without excessive fragmentation.
The surface covers search, URL discovery, fetching, crawling with status/cancel, and page browsing/evaluation. There are minor gaps such as no explicit crawl resume/list operation despite checkpoints being preserved, but core workflows are covered.