Skills/npm/mcp-server

mcp-server@4.14.0

CAUTION

Publisher claims: "MCP server for interacting with Runpod API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher runpod · publishing for 374 daysInstalls 52,025Last detonated 32 min ago

Coverage

Started with a decoy RUNPOD_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in RUNPOD_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
RUNPOD_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
ALP_SINK_SECRETAPI_KEYS_URLMCP_SKIP_CREDENTIAL_CHECKPOSTHOG_API_KEYRUNPOD_API_KEYRUNPOD_ASSISTANT_API_KEYRUNPOD_AUTHED_GRAPHQL_URLConfiguration, not credentials: ALP_SINK_URL, CLAUDE_CONFIG_DIR, ID_PATTERN, KNOWLEDGE_HIDDEN_RULES, KNOWLEDGE_SEARCH_URL, MCP_ANALYTICS_SALT, MCP_REQUEST_LOG_SAMPLE_RATE, MCP_SCHEMA_VALIDATION, MCP_VERBOSE_LOGS, PI_CODING_AGENT_DIR, POSTHOG_HOST, RUNPOD_API_BASE_URL, RUNPOD_MCP_URL, RUNPOD_PUBLIC_GRAPHQL_URL, RUNPOD_SERVERLESS_API_URL, VERCEL
Where it talks to
runpod.io, runpod.ai (its own)Also posthog.com — 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
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names posthog.com as well as its own vendor. The guard injects ALP_SINK_SECRET, API_KEYS_URL, MCP_SKIP_CREDENTIAL_CHECK, POSTHOG_API_KEY, RUNPOD_API_KEY, RUNPOD_ASSISTANT_API_KEY, RUNPOD_AUTHED_GRAPHQL_URL only into requests to runpod.io (and its subdomains) and refuses the rest.

$vet-skills run --secrets ALP_SINK_SECRET=runpod.io,API_KEYS_URL=runpod.io,MCP_SKIP_CREDENTIAL_CHECK=runpod.io,POSTHOG_API_KEY=runpod.io,RUNPOD_API_KEY=runpod.io,RUNPOD_ASSISTANT_API_KEY=runpod.io,RUNPOD_AUTHED_GRAPHQL_URL=runpod.io -- npx -y @runpod/mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 4.12.0

vet-skills diff mcp-server 4.12.0 4.14.0

In the sandbox, this version reached for nothing 4.12.0 did not. Compared from the two recorded runs, not from source.

Only one of the two runs produced a tool list; tools are not compared.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-20 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Credential pass-through configuration; Tool description instructs the agent: credential exfiltration instruction; References a credential file in the home directory. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 56 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
15sprocessdependency install exit 0
35sprocessrelaunched with a decoy RUNPOD_API_KEY (tagged; nothing real)
55sclaimed137 tools with a decoy RUNPOD_API_KEY: list-endpoints, list-templates, run-endpoint, runsync-endpoint, get-job-status, stream-job, cancel-job, retry-job, endpoint-health, purge-endpoint-queue, stream-pod-logs, stream-worker-logs, get-capacity, list-hub-repos, deploy-hub-repo, set-endpoint-gpus, list-public-endpoints, list-guides, read-guide, lookup-concept, search-concepts, search-docs, describe-tool, add-organization-group-member, attach-cost-center-resource
55stools089b5f9800ede297
55stools005c6115b99c667e
55stools34217113a2a01252
55stools6c7536642df20b65
55stoolscf7a8df5ecbdf0a3
55stoolsf68287e4cb5c666c
55stools8e7c2ecf66bf93fc
55stools95c6cb4cf2a6ae39
55stools9bc93e320ddb851f
55stoolsfa7ccb12a95240b3
55stoolsd63b3fa3e73f0198
55stools0b0b1143e30d1a60
55stoolsb26507b9b5b69186
55stools0e9dfde0f8f0ff09
55stoolsa79e36c20c1209f6
55stoolse3f015ae2f441853
55stools562d5c68234e38d8
55stools30aa4174591b83c9
55stoolsc2de7a7255630d55
55stools0065f1a013f9edf6
55stools6245a57678c391c2
55stoolsfa49976eaa507c81
55stoolse04e1acce761959d
55stoolsa706b480119d5778
55stoolsc9bfa1d5a9a4e9ea
55stoolsecfdbbf11adbe018
55stools3ae0e92e3145b69a
55stools2f15bcf8451451a3
55stoolsdc9eb61b5197422e
55stoolsedda345a18ce1477
55stools0a05300f92a00e62
55stoolsdb4001500cd81450
55stools4a035350aeaafb6c
55stoolsed4233dd4b04c6f7
55stools7004677f89e2c403
55stools1330df9ac68b0691
55stools71ec9a46930e9311
55stools40839a78a253d31f
55stoolsb044d1097ab5f93f
55stoolsc0b9f9decfb04a94
55stoolseeb5d34d543cd6ab
55stoolse24e0967e2482f95
55stoolsaec9e3009755274b
55stools8b7549724fbcb0ff
55stools9640552a3f8a6b89
55stools3e6c3e5101873f19
55stoolsb7e23c91294f5bf2
55stoolsd5f8c250f4678c9e
55stoolsbf92445744cfbb5d
55stools9f524fe90dc44561
55stools96ab8ce288de4c06
55stools2bf9f5d96f074cdc
55stools5f2e275460952dda
55stools349976a2a0a238fc
55stools4ae0f92bee9a7246
55stools5e62185ca38c57b2
55stoolsf9915e0bc42584b2
55stools4c0c35f22d1c6813
55stools65aad43e10dd036f
55stools0d0dfa3e38167101
55stools299385991e28be09
55stools360c651621efe1fe
55stools26e4188af57dba56
55stools963335317889a38d
55stools3d6f6452ca290d10
55stoolsae390849f76c7109
55stoolsb9d56b0b96f6ee0a
55stoolsb188522989fd1d3f
55stools9d788cb9ad4b0249
55stools4bf682293ca8797b
55stools47d21637505e5dfc
55stoolsc43bc4bd70c8194e
55stools99746a61740da2f0
55stoolsbad8f0cbb7e3e1aa
55stools0c7390841a7d7fd5
55stools56f85099ba7502a9
55stoolsb0a1587a1c96bab1
55stools3bd2084fbdf81c95
55stools823d519267a026c7
55stoolsf782cc9de4bfed16
55sprocessscript backend runs setup only
55sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationdist/chunk-QB5Z2W52.mjs:10905 · Credential pass-through configuration — agent relays sensitive credentialsthrow new Error("runpod: API key required (set RUNPOD_API_KEY or pass apiKey)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
File type combined with upload actiondist/chunk-QB5Z2W52.mjs:12648 · File type combined with upload action — agent may exfiltrate local data files…xpose, use the machine-readable OpenAPI spec at https://api.runpod.io/v2/openapi.json or the API reference at https://docs.runpod.io/api-reference-v2/overview. Prefer the MCP tools for reads because their results redact secret environment …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Unicode escape sequence detecteddist/chunk-QB5Z2W52.mjs:1531 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagedist/wizard-NVV3UNOG.mjs:836 · npx invocation of non-well-known package — may execute untrusted code" npx @runpod/mcp-server@latest add --list list clients, whether each is detected, and its config file",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Tool description instructs the agent: credential exfiltration instructionmcp:tools/update-endpoint:1 · Instruction aimed at the agent: credential exfiltration instructionret-looking values as [redacted]: never send that placeholder back, it would overwrite the secret with the literal string. Supply the real value or a {{ RUNPFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST01
MEDIUM
npx invocation of non-well-known packagedist/wizard-NVV3UNOG.mjs:1085 · npx invocation of non-well-known package — may execute untrusted codeTo run it without prompts, name the clients: npx @runpod/mcp-server@latest ${subcommand} --client <ids>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
References a credential file in the home directorydist/stdio.mjs:7447 · References a credential file in the home directory…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Unicode escape sequence detecteddist/stdio.mjs:1435 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/stdio.mjs:1545 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsdist/chunk-QB5Z2W52.mjs:7543 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Unicode escape sequence detecteddist/stdio.mjs:2303 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/chunk-QB5Z2W52.mjs:1763 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagedist/stdio.mjs:13485 · npx invocation of non-well-known package — may execute untrusted code" npx @runpod/mcp-server@latest add [--client <ids>] configure your agents (see add --help)",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/wizard-NVV3UNOG.mjs:833 · npx invocation of non-well-known package — may execute untrusted code" npx @runpod/mcp-server@latest add interactive setup (needs a terminal)",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detecteddist/http.cjs:1815 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/http.cjs:2453 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "^[\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]*[Rr][Uu][Nn][Pp][Oo][Dd]:"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/chunk-QB5Z2W52.mjs:2401 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "^[\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]*[Rr][Uu][Nn][Pp][Oo][Dd]:"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/stdio.mjs:1667 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/chunk-QB5Z2W52.mjs:2399 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagedist/wizard-NVV3UNOG.mjs:834 · npx invocation of non-well-known package — may execute untrusted code" npx @runpod/mcp-server@latest add --client <ids> no prompts: configure these clients",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/wizard-NVV3UNOG.mjs:835 · npx invocation of non-well-known package — may execute untrusted code" npx @runpod/mcp-server@latest remove --client <ids> no prompts: remove Runpod from them",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/stdio.mjs:7447 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Unicode escape sequence detecteddist/chunk-QB5Z2W52.mjs:1641 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsdist/http.cjs:7595 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
References a credential file in the home directorydist/http.cjs:7595 · References a credential file in the home directory…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Credential pass-through configurationdist/http.cjs:11150 · Credential pass-through configuration — agent relays sensitive credentialsthrow new Error("runpod: API key required (set RUNPOD_API_KEY or pass apiKey)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Unicode escape sequence detecteddist/http.cjs:1583 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Credential pass-through configurationdist/stdio.mjs:10978 · Credential pass-through configuration — agent relays sensitive credentialsthrow new Error("runpod: API key required (set RUNPOD_API_KEY or pass apiKey)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Unicode escape sequence detecteddist/http.cjs:1693 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagedist/stdio.mjs:13486 · npx invocation of non-well-known package — may execute untrusted code" npx @runpod/mcp-server@latest remove --client <ids> remove Runpod from your agents"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/stdio.mjs:13128 · File type combined with upload action — agent may exfiltrate local data files…xpose, use the machine-readable OpenAPI spec at https://api.runpod.io/v2/openapi.json or the API reference at https://docs.runpod.io/api-reference-v2/overview. Prefer the MCP tools for reads because their results redact secret environment …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
References a credential file in the home directorydist/chunk-QB5Z2W52.mjs:7543 · References a credential file in the home directory…y is an authorized_keys-style line: `<type> <base64-key> [comment]`, e.g. from `~/.ssh/id_ed25519.pub`. Send `[]` to remove all keys.", examples: [ …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Unicode escape sequence detecteddist/stdio.mjs:2305 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "^[\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]*[Rr][Uu][Nn][Pp][Oo][Dd]:"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actiondist/http.cjs:13024 · File type combined with upload action — agent may exfiltrate local data files…xpose, use the machine-readable OpenAPI spec at https://api.runpod.io/v2/openapi.json or the API reference at https://docs.runpod.io/api-reference-v2/overview. Prefer the MCP tools for reads because their results redact secret environment …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/stdio.mjs:13484 · npx invocation of non-well-known package — may execute untrusted code" RUNPOD_API_KEY=<key> npx @runpod/mcp-server@latest run the MCP server over stdio",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detecteddist/http.cjs:2451 · Unicode escape sequence detected — may contain obfuscated payloadspattern: "[^\\t-\\r \x85\xA0\u1680\u2000-\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF]",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈48 tok
1 file · 26 in bundle
Tool list per prompt
≈32,500 tok
137 tools · 237 per tool
Handshake
3776 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 390

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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim runpod: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. 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.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim runpodPropose a patch to the maintainer