mcp-server-for-ynab@6.2.1
CAUTIONPublisher claims: "Local MCP server for YNAB budget operations" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
Before you give it your token
- It will ask for
MAX_TOKEN_FILE_BYTESSENTRY_DSNYNAB_API_TOKENConfiguration, not credentials: KEY, YNAB_ALLOW_WRITES, YNAB_DISABLE_AGENT_CONFIG_FALLBACK, YNAB_HOSTED_URL, YNAB_MCP_NO_AUTOSTART, YNAB_OP_CACHE, YNAB_RATE_LIMIT_PER_HOUR, YNAB_SMOKE_OP_ITEM, YNAB_SMOKE_OP_VAULT- Where it talks to
- no vendor host named in the codeAlso ynab.com, ames-ynab.link — 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
- 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 ynab.com, ames-ynab.link as well as its own vendor. The guard injects MAX_TOKEN_FILE_BYTES, SENTRY_DSN, YNAB_API_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.
What changed since 6.1.1
vet-skills diff mcp-server-for-ynab 6.1.1 6.2.1In the sandbox, this version reached for nothing 6.1.1 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) on 2026-11-21 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Image alt text carrying instructions; Collects environment variables by secret-like names; Image alt text carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 33 s · 2 scenariosStatic findings
Generate Personal Access TokenFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Object.entries(process.env).filter(([, value]) => typeof value === "string"),Fix: Never read or enumerate credential locations; accept a documented environment variable instead.New Personal Access TokenFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.console.log(`Built ${outputPath} (${size} bytes)`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.`Use --published to test npx -y ${packageJson.name}@latest from /tmp.`,Fix: Pin versions and sources; vendor anything fetched at install time.values: pickYnabValues(settings?.env || {}),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log(`Generated ${outputPath} from ${sourcePath}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log("Batch category+approval update verified by post-write refetch");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.label: `npx -y ${options.packageSpec}`,Fix: 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 @oliverames/mcp-server-for-ynab@6.2.1 as of 33 min ago. This is the package itself, not its dependencies.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim oliverames: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Collects environment variables by secret-like names≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- 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.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.