adt-mcp@0.4.59
VERIFIED· not startedPublisher claims: "MCP server for SAP ADT operations – exposes adt-cli features as MCP tools" 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: 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
MCP_AUTH_TOKENOAUTH_AUDIENCEOAUTH_ISSUEROAUTH_JWKS_URIOAUTH_REQUIRED_SCOPESOAUTH_USER_CLAIMTRUST_FORWARDED_AUTHor--auth-token/--trust-forwarded-auth/--oauth-issuer/--oauth-audience/--oauth-jwks-uri/--oauth-required-scope/--oauth-user-claimConfiguration, not credentials: ADT_CONFIG_FILE, MCP_ALLOWED_HOSTS, MCP_CORS_ORIGIN, MCP_HOST, MCP_PORT, MCP_TLS_CERT, MCP_TLS_KEY, SAP_SYSTEMS_FILE, SAP_SYSTEMS_JSON- Where it talks to
- no vendor host named in the codeAlso sap.com — 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 sap.com as well as its own vendor. The guard injects MCP_AUTH_TOKEN, OAUTH_AUDIENCE, OAUTH_ISSUER, OAUTH_JWKS_URI, OAUTH_REQUIRED_SCOPES, OAUTH_USER_CLAIM, TRUST_FORWARDED_AUTH 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 2026-11-19 and scored it 87/100 (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 · 8 s · 2 scenarios · 0 deviationsStatic findings
text: "sap_connect requires HTTP transport (Mcp-Session-Id). Stdio callers should pass credentials per tool call instead."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if (entry.username || entry.password) process.stderr.write(`[multi-system] warning: system '${id}' contains credentials in config; dropping them. Pass credentials via sap_connect at runtime.\n`);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* → spin up a new McpServer + StreamableHTTPServerTransport pair,Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.…nationContextRegistry, createHttpMcpHandler, createMcpInvocationVerifier, createMcpServer, createSessionRegistry, isMcpToolAllowed, loadMultiSystemConfig, operationClassForMcpTool, parseDelegatedAssistantReadPolicy, parseSafeExecutePolicy,…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.* Start with: npx adt-mcpFix: 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 @abapify/adt-mcp@0.4.59 as of 4 h ago. This is the package itself, not its dependencies.