token-context-mcp@0.3.10
CAUTION· not startedPublisher claims: "On-demand, local code-context MCP server for AI coding agents with Tree-sitter AST & provenance-aware retrieval." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
TOKEN_CONTEXT_ADMIN_TOKENTOKEN_CONTEXT_BODY_MODE_BEHAVIORTOKEN_CONTEXT_CONFIGTOKEN_CONTEXT_DEP_VENDOREDTOKEN_CONTEXT_FAMILY_CAPTOKEN_CONTEXT_FTS_DOC_COMMENTSTOKEN_CONTEXT_FTS_INTERFACE_DOCTOKEN_CONTEXT_FTS_WORD_FORMSTOKEN_CONTEXT_GUI_DEBUGTOKEN_CONTEXT_IMPL_RANKINGTOKEN_CONTEXT_INDEX_WORKERSTOKEN_CONTEXT_OLLAMA_ENDPOINTTOKEN_CONTEXT_OVERLOAD_COLLAPSETOKEN_CONTEXT_QUERY_WORD_FORMSTOKEN_CONTEXT_TRACE_SQL- Where it talks to
- token-context-mcp.local (its own)Also in-toto.io, slsa.dev — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names in-toto.io, slsa.dev as well as its own vendor. The guard injects TOKEN_CONTEXT_ADMIN_TOKEN, TOKEN_CONTEXT_BODY_MODE_BEHAVIOR, TOKEN_CONTEXT_CONFIG, TOKEN_CONTEXT_DEP_VENDORED, TOKEN_CONTEXT_FAMILY_CAP, TOKEN_CONTEXT_FTS_DOC_COMMENTS, TOKEN_CONTEXT_FTS_INTERFACE_DOC, TOKEN_CONTEXT_FTS_WORD_FORMS, TOKEN_CONTEXT_GUI_DEBUG, TOKEN_CONTEXT_IMPL_RANKING, TOKEN_CONTEXT_INDEX_WORKERS, TOKEN_CONTEXT_OLLAMA_ENDPOINT, TOKEN_CONTEXT_OVERLOAD_COLLAPSE, TOKEN_CONTEXT_QUERY_WORD_FORMS, TOKEN_CONTEXT_TRACE_SQL only into requests to token-context-mcp.local (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
mcp-name: io.github.MCK564/token-context-mcpFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.except Exception: # a broken render must not kill the event loopFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.".venv", "venv", "env", ".env", "node_modules", ".pytest_cache",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.check_output(["nvidia-smi", "--query-gpu=name", "--format=csv,noheader"], text=True, timeout=2)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for token-context-mcp@0.3.10 as of 38 min ago. This is the package itself, not its dependencies.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim mck564: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.