ai-mcp-server@6.1.7
CAUTION· not startedPublisher claims: "MemberJunction: Model Context Protocol (MCP) - Server Implementation" 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: Caution 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
MCP_JWT_SECRETMIN_JWT_SECRET_LENGTHMJ_API_KEYWEB_CLIENT_SECRETConfiguration, not credentials: DB_DATABASE, WEB_CLIENT_ID- Where it talks to
- no vendor host named in the codeAlso microsoftonline.com, windows.net, evil.example — 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 microsoftonline.com, windows.net, evil.example as well as its own vendor. The guard injects MCP_JWT_SECRET, MIN_JWT_SECRET_LENGTH, MJ_API_KEY, WEB_CLIENT_SECRET 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 2026-11-11 and scored it 77/100 (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; Access to sensitive file paths; Credential pass-through configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 31 s · 2 scenarios · 0 deviationsStatic findings
* Configures the proxy token validation settings.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* @returns Path to the .env file if found, undefined otherwiseFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* Creates a JWT Issuer for signing proxy tokens.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.isProxyToken: (token: string) => boolean;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.isProxyToken,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.import { hasAuthProviders, setProxyTokenConfig } from './auth/TokenValidator.js';Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* npx @memberjunction/ai-mcp-serverFix: Pin versions and sources; vendor anything fetched at install time.console.log("Example: npx @memberjunction/ai-mcp-server --include \"Get_Users_*,Run_Agent\"");Fix: Pin versions and sources; vendor anything fetched at install time.proxyTokenConfig = config;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* Searches upward from the current directory for a .env file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* Configuration for proxy token validation.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* npx @memberjunction/ai-mcp-server --include "Get_*,Run_Agent"Fix: Pin versions and sources; vendor anything fetched at install time.interface ProxyTokenConfig {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* @param config - Proxy token configurationFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.function isProxyToken(token) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.let proxyTokenConfig;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* - Load dotenv first (above) which populates process.env with DB credentials from .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* npx @memberjunction/ai-mcp-server --include "Get_*,Run_Agent"Fix: Pin versions and sources; vendor anything fetched at install time.* 1. Environment variables (.env file via dotenv - searches upward from cwd)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* npx @memberjunction/ai-mcp-serverFix: Pin versions and sources; vendor anything fetched at install time.setProxyTokenConfig({Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// Initialize configuration (loads .env and mj.config.cjs)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.export function setProxyTokenConfig(config) {Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* npx @memberjunction/ai-mcp-server --list-toolsFix: Pin versions and sources; vendor anything fetched at install time.// Initialize configuration (loads .env and mj.config.cjs)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* 1. Environment variables (.env file via dotenv - searches upward from cwd)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* This mimics cosmiconfig's search behavior so the .env file is foundFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* Configures the proxy token validation settings.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(`SSE endpoint: http://localhost:${mcpServerPort}/mcp/sse`);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them./** Issuer - always "urn:mj:mcp-server" for proxy tokens */Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* @param config - Proxy token configurationFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* Creates a JWT Issuer for signing proxy tokens.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* Set via setProxyTokenConfig() when OAuth proxy JWT signing is enabled.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| `Run_<Prompt>_Prompt` | Execute a configured AI prompt with template data |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.* npx @memberjunction/ai-mcp-server --list-toolsFix: Pin versions and sources; vendor anything fetched at install time.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 @memberjunction/ai-mcp-server@6.1.7 as of 3d ago. This is the package itself, not its dependencies.
What would make this Verified
3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim memberjunction: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- 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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.