fireflyiii-mcp@1.0.0
VERIFIED· startup onlyPublisher claims: "MCP server for Firefly III personal finance manager" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
- Needs
- FIREFLY_TOKEN — 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.
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
FIREFLY_OAUTH_CLIENT_IDFIREFLY_TOKENConfiguration, not credentials: FIREFLY_DEBUG, FIREFLY_URL, MCP_ALLOWED_REDIRECT_PREFIXES, MCP_BASE_URL, MCP_GROUPS, MCP_PRESET, MCP_READ_ONLY- Where it talks to
- no vendor host named in the codeAlso claude.ai, claude.com, attacker.test — 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
- 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 claude.ai, claude.com, attacker.test as well as its own vendor. The guard injects FIREFLY_OAUTH_CLIENT_ID, FIREFLY_TOKEN 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; startup only; authenticated tool behavior not tested) on 2026-11-11 and scored it 81/100 (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 (it asks for FIREFLY_TOKEN); 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 · 53 s · 2 scenarios · 0 deviationsStatic findings
// comparing). The one exception is the port-wildcard form 'http://192.168.1.10:' (aFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.'See .env.example for configuration instructions.\n');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* memory or, past V8's maximum string length, throw inside the stream listener and kill the process.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."dev": "dotenv -e .env -- tsx src/index.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…ng, port: number): Promise<void>; export declare function startHttpServer(createMcpServer: () => McpServer, host: string, requestedPort: number, portWasExplicit: boolean, oauthClientId: string | undefined, fireflyUrl: string, tryListenFn?:…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.* memory or, past V8's maximum string length, throw inside the stream listener and kill the process.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.".env.example"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.export declare function createMcpRequestHandler(createMcpServer: () => McpServer): (req: http.IncomingMessage, res: http.ServerResponse) => Promise<void>;Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."test:integration": "dotenv -e .env.test -- vitest run src/tests/integration.test.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'See .env.example for configuration instructions.\n');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."build": "tsc && chmod +x dist/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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 @daften/fireflyiii-mcp@1.0.0 as of 3d ago. This is the package itself, not its dependencies.