token-save-mcp@0.4.1
VERIFIED· not startedPublisher claims: "MCP server that keeps large files out of your coding agent's context by delegating reads to a cheap worker model. Enforced by a hook, measured per call." 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: Verified 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
TOKENSAVE_API_KEYTOKENSAVE_BASE_URLTOKENSAVE_HOOK_MODETOKENSAVE_LEDGERTOKENSAVE_LOG_DIRTOKENSAVE_MAX_CONCURRENCYTOKENSAVE_MAX_CORPUS_BYTESTOKENSAVE_MAX_RETRIESTOKENSAVE_MIN_LINESTOKENSAVE_MODELTOKENSAVE_NO_LEDGERTOKENSAVE_PROVIDERTOKENSAVE_TIMEOUT- Where it talks to
- no vendor host named in the codeAlso ollama.com, openrouter.ai, deepseek.com, groq.com, shields.io — 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 ollama.com, openrouter.ai, deepseek.com, groq.com, shields.io as well as its own vendor. The guard injects TOKENSAVE_API_KEY, TOKENSAVE_BASE_URL, TOKENSAVE_HOOK_MODE, TOKENSAVE_LEDGER, TOKENSAVE_LOG_DIR, TOKENSAVE_MAX_CONCURRENCY, TOKENSAVE_MAX_CORPUS_BYTES, TOKENSAVE_MAX_RETRIES, TOKENSAVE_MIN_LINES, TOKENSAVE_MODEL, TOKENSAVE_NO_LEDGER, TOKENSAVE_PROVIDER, TOKENSAVE_TIMEOUT only into requests to the host you bind (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 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
else sudo apt-get update && sudo apt-get install -y jq; fiFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.S = importlib.util.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.token-save-mcp in actionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.<summary><b>What if I have no API key?</b></summary> `init` will show you this: ``` This tool sends files to a worker model of YOUR choosing. Nothing is connectFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.res = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._spec.loader.exec_module(C)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.res = subprocess.run(["claude", "mcp", "list"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.C = importlib.util.module_from_spec(_spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell._spec.loader.exec_module(S)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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-save-mcp@0.4.1 as of 38 min ago. This is the package itself, not its dependencies.