Skills/npm/pi-session-mcp

pi-session-mcp@0.21.0

VERIFIED· not started

Publisher claims: "Local stdio MCP server that lets Codex and Claude Code delegate work to configured Pi coding-agent sessions" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher plagor44-ux · publishing for 39 daysInstalls 6,179Last detonated 29 h ago
$claude mcp add pi-session-mcp -- npx -y pi-session-mcp
WatchReport an issue

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
PI_WRITER_NO_CREDENTIAL_REFRESH or --max-tokensConfiguration, not credentials: CLAUDE_CONFIG_DIR, PI_SESSION_MCP_CONFIG, PI_SESSION_MCP_WRITER_GUARD, PI_WRITER_LEASE_FD, XDG_RUNTIME_DIR
Where it talks to
no vendor host named in the code
What the honeypot saw
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. It asks for PI_WRITER_NO_CREDENTIAL_REFRESH and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- npx -y pi-session-mcp

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 2026-11-13 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 · 13 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
13sprocessdependency install exit 1 · (Use `node --trace-warnings ...` to show where the warning was created) npm error Cannot read properties of null (reading 'edgesOut') npm error A complete log of this run can be found in: /tmp/ks-detonate-VPRZwh/task/home/.npm/_logs/2026-11-13T08_42_10_789Z-debug-0.log
13sclaimednot started: dependency install failed (exit 1); the server itself was not observed
13sprocessscript backend runs setup only
13sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/setup-process.js:59 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files… ["ignore", "pipe", "pipe", ...(runOptions?.inheritFds ?? [])], env: runOptions?.env ? { ...(options.env ?? process.env), ...runOptions.env } : options.env, cwd: ru…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commanddist/sandbox-shell.js:479 · Process kill command — agent can terminate processesreturn { child, closed, gate, kill };Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commanddist/doctor.js:200 · File permission modification command — agent changes file ownership/permissionsreturn failure("writer_lease_directory", "writer lease", "repair the lease directory in place (owner and chmod 700); never move or delete it or its lock files");Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commanddist/sandbox-shell.js:557 · Process kill command — agent can terminate processesconst { child, closed, gate, kill } = running;Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commanddist/doctor.js:238 · File permission modification command — agent changes file ownership/permissionsreturn failure("event_spool_root", "event spool", `remove group and other permissions from the ${label} directory (chmod 700)`);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actiondist/routing/learn.js:116 · File type combined with upload action — agent may exfiltrate local data files… (key, value) VALUES ('last_refresh_at', '')").run(); return input.store.db.prepare("UPDATE routing_meta SET value = ? WHERE key = 'last_refresh_at' AND value <= ?").run(input.now.toISOString(), new Date(input.now.getTime() - 86400000).toI…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/sandbox-shell.js:494 · Process kill command — agent can terminate processesconst { child, closed, gate, kill } = running;Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsdist/setup-process.js:419 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (runOptions?.env !== undefined || runOptions?.inheritFds !== undefined || released || unsafe || pending || runSignal?.aborted || !child.connected)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commanddist/sandbox-shell.js:406 · Process kill command — agent can terminate processesconst kill = () => {Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈64 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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 pi-session-mcp@0.21.0 as of 28 h ago. This is the package itself, not its dependencies.

pi-session-mcp@0.21.0 safety verdict: Verified (not started) — KillerSkills