tor-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOR_MCP_TOR_PATH | No | Use this Tor binary instead of the downloaded one. | |
| TOR_MCP_CACHE_DIR | No | Directory where the downloaded Tor lives. | ~/.cache/tor-mcp |
| TOR_MCP_ARCHIVE_DIR | No | Directory where `tor_archive` saves archived pages. | ~/tor-mcp-archive |
| TOR_MCP_CHROME_PATH | No | Chromium-based browser path used by `tor_browse`. Auto-detected by default. | |
| TOR_MCP_NO_DOWNLOAD | No | Set to `1` to never download Tor. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tor_statusA | Start Tor if needed and report whether it is connected, the Tor version and the current exit IP as seen by websites. Call this first to confirm traffic really goes through Tor. |
| tor_fetchA | Download a web page (including .onion addresses) through Tor and return its readable text as Markdown plus its links. Fast and light: no JavaScript runs. Includes retrieval time and SHA-256 of the raw response. Use tor_browse for pages that need JavaScript or interaction. |
| tor_browseA | Open a URL (including .onion) in a headless Chromium that routes all traffic through Tor, with a throwaway in-memory profile. Returns readable text and links. Use tor_click, tor_type and tor_screenshot afterwards. Set javascript=false for a safer, Tor-Browser-'Safest'-like mode. |
| tor_clickA | Click an element on the page opened by tor_browse, by CSS selector or by visible text. Returns the resulting page. |
| tor_typeA | Fill a field on the open page (e.g. a search box) and optionally press Enter. Never use this to enter passwords, real names or other personal data. |
| tor_screenshotA | Take a PNG screenshot of the page opened by tor_browse. |
| tor_archiveA | Save a copy of a page for reporting: HTML, readable Markdown, a screenshot (browser mode) and manifest.json with UTC time, final URL, HTTP status, Tor exit IP and a SHA-256 for every file. Saved under ~/tor-mcp-archive (or TOR_MCP_ARCHIVE_DIR). This is the only tool that writes to disk. |
| tor_new_identityA | Switch to new Tor circuits (new exit IP for new connections) and wipe the browser's cookies, storage and open page. |
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
Each tool targets a distinct action: status check, static fetch, JS-capable browsing, page interaction (click/type/screenshot), archiving, and circuit reset. The only potential overlap — tor_fetch vs tor_browse — is explicitly resolved in both descriptions (lightweight no-JS retrieval vs headless Chromium with interaction follow-ups). tor_click, tor_type and tor_screenshot are clearly scoped as continuations of a tor_browse session.
All names share a uniform tor_ snake_case prefix with single-word verbs (fetch, browse, click, type, screenshot, archive), which is highly predictable. Minor deviation: tor_status and tor_new_identity are noun-phrase style rather than verb_noun, but semantics remain obvious.
Eight tools is well within the sweet spot and each one maps to a real capability: connectivity check, two retrieval modes, three interaction primitives, evidence capture, and identity rotation. Nothing feels redundant or padded for a Tor browsing server.
The surface covers the full core lifecycle: verify Tor connectivity, retrieve pages (static or JS), interact, capture evidence, archive, and rotate identity. Gaps are minor — no back/forward navigation or history control, no explicit session close/cleanup beyond tor_new_identity, and no scroll or multi-element form submission — but agents can largely work around these.