sf-mcp-server@0.1.1
VERIFIED· not startedPublisher claims: "An independent, open-source MCP server for Salesforce (REST, Bulk API 2.0, Composite) — not a Salesforce product." 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_SERVER_TOKENSF_AUTH_FLOWSF_CLIENT_SECRETSF_PKCE_TOKEN_CACHEConfiguration, not credentials: MCP_HOST, MCP_PORT, MCP_TRANSPORT, SF_API_VERSION, SF_ELICITATION_ENABLED, SF_PKCE_REDIRECT_PORT, SF_PUBSUB_HOST, SF_PUBSUB_PORT- Where it talks to
- no vendor host named in the codeAlso salesforce.com, grpc.io — 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 salesforce.com, grpc.io as well as its own vendor. The guard injects MCP_SERVER_TOKEN, SF_AUTH_FLOW, SF_CLIENT_SECRET, SF_PKCE_TOKEN_CACHE 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 2026-11-18 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 · 0 s · 2 scenarios · 0 deviationsStatic findings
print(f"Cached refresh token to {result['cache_path']} (chmod 600).")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."MCP_SERVER_TOKEN is required when MCP_TRANSPORT=http "Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Reads the same .env the server does (via Settings.from_env()) — run it fromFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 sf-mcp-server@0.1.1 as of 1 h ago. This is the package itself, not its dependencies.