Skills/npm/mcp

mcp@0.0.140

VERIFIED· not started

Publisher claims: "Tempo MCP server for Claude Code, Codex, Cursor, and any other MCP-compatible host. One server exposing Tempo's issues, docs, comments, agents, scripts, Slack, Linear, and canvas toolsets." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher tempo-ai · publishing for 80 daysInstalls 7,048Last detonated 6 h ago
$claude mcp add mcp -- npx -y @tempo-ai/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
ENV_TOKEN_VARTEMPO_AUTH_URLConfiguration, not credentials: TEMPO_CONVEX_SITE_URL, TEMPO_CONVEX_URL, TEMPO_LOGIN_SITE_URL, TEMPO_MCP_HOME, TEMPO_MCP_NO_BROWSER, TEMPO_MCP_READONLY, TEMPO_MCP_SIGN_IN_WAIT_MS
Where it talks to
no vendor host named in the codeAlso tempo.build, convex.site, convex.cloud — not the publisher's domain; check what for before connecting.
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, and read the third-party hosts first. The code names tempo.build, convex.site, convex.cloud as well as its own vendor. The guard injects ENV_TOKEN_VAR, TEMPO_AUTH_URL only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @tempo-ai/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 2026-11-14 and scored it 90/100 (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 · 4 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.0sprocessdependency install exit 1 · npm error code EUNSUPPORTEDPROTOCOL npm error Unsupported URL Type "workspace:": workspace:* npm error A complete log of this run can be found in: /tmp/ks-detonate-qaHost/task/home/.npm/_logs/2026-11-14T07_22_38_502Z-debug-0.log
4.0sclaimednot started: dependency install failed (exit 1); the server itself was not observed
4.0sprocessscript backend runs setup only
4.0sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/chunk-M5AY262E.js:85 · npx invocation of non-well-known package — may execute untrusted code"Not signed in. Use a Tempo tool from your agent to get a sign-in link, or run `npx -y @tempo-ai/mcp login`."Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/token-TCKG4IBA.js:61 · npx invocation of non-well-known package — may execute untrusted codeconsole.error("Not signed in. Run `npx -y @tempo-ai/mcp login` first.");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageREADME.md:136 · Authorization escalation language · informational: not an instruction file4. In a chat, enable the connector under **Plus → More → Developer mode**.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:139 · Prompt injection — known jailbreak technique reference · informational: not an instruction filedeep-research tools; Developer mode unlocks full tool calling.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagedist/chunk-M5AY262E.js:20 · npx invocation of non-well-known package — may execute untrusted codeclaude mcp add tempo -- npx -y @tempo-ai/mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.md:132 · Prompt injection — known jailbreak technique reference · informational: not an instruction file**Advanced settings** → enable **Developer mode**.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagedist/chunk-4R6XIZCX.js:1048 · npx invocation of non-well-known package — may execute untrusted code"Not signed in to Tempo. Run `npx -y @tempo-ai/mcp login` in a terminal, or set TEMPO_AUTH_TOKEN for headless environments."Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageREADME.md:138 · Authorization escalation language · informational: not an instruction fileNote: without Developer mode, ChatGPT connectors only run search-styleFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:138 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileNote: without Developer mode, ChatGPT connectors only run search-styleFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:139 · Authorization escalation language · informational: not an instruction filedeep-research tools; Developer mode unlocks full tool calling.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/chunk-4R6XIZCX.js:185 · npx invocation of non-well-known package — may execute untrusted code"Not signed in to Tempo. Retry the tool to get a sign-in link, or run `npx -y @tempo-ai/mcp login`."Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Prompt injectionREADME.md:136 · Prompt injection — known jailbreak technique reference · informational: not an instruction file4. In a chat, enable the connector under **Plus → More → Developer mode**.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagedist/chunk-4R6XIZCX.js:1093 · npx invocation of non-well-known package — may execute untrusted code"[tempo-mcp] Tempo session expired. Run `npx -y @tempo-ai/mcp login` to sign in again."Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageREADME.md:132 · Authorization escalation language · informational: not an instruction file**Advanced settings** → enable **Developer mode**.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/chunk-M5AY262E.js:104 · npx invocation of non-well-known package — may execute untrusted code"Signed out. The next Tempo tool call from your agent will prompt for sign-in (or run `npx -y @tempo-ai/mcp login`)."Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/chunk-4R6XIZCX.js:197 · npx invocation of non-well-known package — may execute untrusted code"Tempo session expired. Retry the tool to get a sign-in link, or run `npx -y @tempo-ai/mcp login`."Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈82 tok
1 file · 11 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 @tempo-ai/mcp@0.0.140 as of 2 h ago. This is the package itself, not its dependencies.