Skills/npm/mcp-server

mcp-server@5.1.79

VERIFIED· startup only

Publisher claims: "Didit MCP Server - AI agent integration for identity verification APIs" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher didit-protocol · publishing for 266 daysInstalls 4,633Last detonated 15 min ago
$claude mcp add mcp-server -- npx -y @didit-protocol/mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

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
DIDIT_ACCESS_TOKENDIDIT_AUTH_BASE_URLDIDIT_AUTH_ISSUERDIDIT_EVENTS_SECRETDIDIT_MCP_CREDENTIALS_FILEDIDIT_OIDC_AUTHORIZE_URLDIDIT_OIDC_TOKEN_URLMCP_AUTHORIZATION_SERVER_ORIGINMCP_OAUTH_CLIENT_IDMCP_OAUTH_CLIENT_SECRETMCP_OAUTH_INTROSPECT_URLMCP_TOKEN_VERIFY_MODEMCP_WEBHOOK_POLL_MSConfiguration, not credentials: DIDIT_API_BASE_URL, DIDIT_DEVICE_NAME, DIDIT_DOCS_MCP_URL, DIDIT_JWKS_URL, DIDIT_OIDC_DISCOVERY_URL, DIDIT_OIDC_REGISTRATION_URL, DIDIT_READ_ONLY, DIDIT_TOOLSETS, ECS_CONTAINER_METADATA_URI_V4, MCP_CONSOLE_CLIENT_IDS, MCP_DEFAULT_APP, MCP_DEFAULT_ORG, MCP_DEFAULT_TOOLSETS, MCP_INTROSPECTION_CACHE_TTL_MS, MCP_JSON_BODY_LIMIT, MCP_PERMISSION_MODE, MCP_PORT, MCP_PUBLIC_DISCOVERY, MCP_RESOURCE_URI, MCP_SCOPES_SUPPORTED, MCP_SERVER_VERSION, WAKESHIFT_KEY
Where it talks to
didit.me (its own)Also standardwebhooks.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
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names standardwebhooks.com as well as its own vendor. The guard injects DIDIT_ACCESS_TOKEN, DIDIT_AUTH_BASE_URL, DIDIT_AUTH_ISSUER, DIDIT_EVENTS_SECRET, DIDIT_MCP_CREDENTIALS_FILE, DIDIT_OIDC_AUTHORIZE_URL, DIDIT_OIDC_TOKEN_URL, MCP_AUTHORIZATION_SERVER_ORIGIN, MCP_OAUTH_CLIENT_ID, MCP_OAUTH_CLIENT_SECRET, MCP_OAUTH_INTROSPECT_URL, MCP_TOKEN_VERIFY_MODE, MCP_WEBHOOK_POLL_MS only into requests to didit.me (and its subdomains) and refuses the rest.

$vet-skills run --secrets DIDIT_ACCESS_TOKEN=didit.me,DIDIT_AUTH_BASE_URL=didit.me,DIDIT_AUTH_ISSUER=didit.me,DIDIT_EVENTS_SECRET=didit.me,DIDIT_MCP_CREDENTIALS_FILE=didit.me,DIDIT_OIDC_AUTHORIZE_URL=didit.me,DIDIT_OIDC_TOKEN_URL=didit.me,MCP_AUTHORIZATION_SERVER_ORIGIN=didit.me,MCP_OAUTH_CLIENT_ID=didit.me,MCP_OAUTH_CLIENT_SECRET=didit.me,MCP_OAUTH_INTROSPECT_URL=didit.me,MCP_TOKEN_VERIFY_MODE=didit.me,MCP_WEBHOOK_POLL_MS=didit.me -- npx -y @didit-protocol/mcp-server

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

What changed since 5.1.74

vet-skills diff mcp-server 5.1.74 5.1.79

In the sandbox, this version reached for nothing 5.1.74 did not. Compared from the two recorded runs, not from source.

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; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 86/100 (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 · 29 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
9.2sprocessdependency install exit 0
29sclaimedstartup only: exited (0) before answering · '/tmp/ks-detonate-KjB9G7/task/home/work/acme-api/.claude/skills/mcp-server/dist/index.js' ] } Node.js v22.23.5
29sprocessscript backend runs setup only
29sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/index.js:1201 · npx invocation of non-well-known package — may execute untrusted code…ted connector - authentication is handled by OAuth. Use the local stdio server (npx @didit-protocol/mcp-server) for account setup.` }], isError: true, }; …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/tools/members.js:227 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"ONCE: write it straight to the project's secret store or .env and never repeat it in the chat. Pick the " +Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/tools/members.js:96 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileshint: "Say which application the key is for and where you will store it (a secret manager or the project's .env, never committed).",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/tools/members.js:126 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesnext_steps: "Store api_key now in the project's secret store or .env (never commit it, never repeat it in the chat): it is " +Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/index.js:1218 · npx invocation of non-well-known package — may execute untrusted codetext: `Tool '${name}' is not available to a remote connector. Copy the API key from the application's page in the Didit console, or use the local stdio server (npx @didit-protocol/mcp-server).`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/security.js:138 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* magic-bytes allow-list (a `.env` would also fail the sniff). MatchedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Refusal suppressionREADME.md:865 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file…eps a user whose sign-in failed on the wallet step to try again: the session is never declined for it and no document is offered. | | `minimum_age` | integer \| null | integ…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsdist/security.d.ts:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* (so `.env`, `package.json`, source, archives, executables can never be read).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/security.js:142 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env", ".env.local", ".env.development", ".env.production", ".env.test",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈57 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

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