Skills/npm/mcp-server-for-ynab

mcp-server-for-ynab@6.2.1

CAUTION

Publisher claims: "Local MCP server for YNAB budget operations" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher oliverames · publishing for 248 daysInstalls 3,051Last detonated 1 h ago

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.

$vet-skills run --net declared -- npx -y @oliverames/mcp-server-for-ynab

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 6.2.1

In 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 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
12sprocessdependency install exit 0
32sfilesystemread ~/.codex/config.toml · ~/.claude/settings.json outside project
32sclaimed45 tools: preview_write_tool, get_user, list_budgets, get_budget, get_budget_settings, list_accounts, get_account, list_categories, get_category, get_month_category, list_payees, get_payee, list_payee_locations, get_payee_location, get_payee_locations_by_payee, list_months, get_month, list_money_movements, get_money_movements_by_month, list_money_movement_groups, get_money_movement_groups_by_month, get_transactions, search_transactions, resolve_matched_transactions, get_transaction
32stoolsd2dd6134a96cac92
32stools152fe34b4dfd83f8
32stoolscd032a8cbd4fb5cb
32stoolsde67931fd525530f
32stools007f689863262b69
32stools8a3c6c03b7625db5
32stoolse0bb980ea20174b8
32stools43115a7f9de33cca
32stools21b1ae25719635ea
32stoolsf05434a44b453e7a
32stoolsc2711c3c108654de
32stoolsdb31e0e6cbed82b7
32stoolse9f862493bb2c0af
32stools09243cfc2604effe
32stools2e476b2bc10703d0
32stoolsb08323352720a6dd
32stools305b2b6556cf0ee3
32stoolscc1f5aa82f31bcc5
32stools3fee1420746f1c61
32stools60b6a6aeae8aae3d
32stoolsea4defce693f2544
32stools712d95a9b826021e
32stools0a2d13778ea4dcf7
32stools8bc5510256d029d4
32stools3fca7cdc75fd2592
32stools7e386c761b02a48d
32stools9758e1b5ee49ef55
32stools09ec526e957e66c8
32stools9a34ad78f2e6f7f7
32stoolsaa4d9dc82069a758
32stools7d3441ea6e228796
32stools8893403bd2b48247
32stoolse0dbbe5f9d845c6e
32stools4e4daa834d2cc414
32stoolsc95487fb9389923c
32stools33c48f9db2a811d5
32stoolse2ea470516444608
32stools27481d0b01e136de
32stools95509091f7094b15
32stools6375a3498eb18540
32stoolsb4e400321a7d9130
32stoolsbdefaed863ccb861
32stoolsac3660c8c992d1a1
32stools9213711e587ee613
32stools0603ae46d90059f7
32sprocessscript backend runs setup only
32sprocessno install scripts to re-run

Static findings

HIGH
Image alt text carrying instructionsdocs/api-documentation.md:146 · Image alt text carrying instructionsGenerate Personal Access TokenFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collects environment variables by secret-like namesscripts/test-safety-model.mjs:57 · Collects environment variables by secret-like namesObject.entries(process.env).filter(([, value]) => typeof value === "string"),Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Image alt text carrying instructionsdocs/api-documentation.md:148 · Image alt text carrying instructionsNew Personal Access TokenFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionscripts/build-mcpb.mjs:142 · File type combined with upload action — agent may exfiltrate local data filesconsole.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.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/lib/smoke-client.mjs:33 · npx invocation of non-well-known package — may execute untrusted code`Use --published to test npx -y ${packageJson.name}@latest from /tmp.`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsindex.js:261 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvalues: pickYnabValues(settings?.env || {}),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/generate-worker-icon-assets.mjs:123 · File type combined with upload action — agent may exfiltrate local data filesconsole.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.
AST07
MEDIUM
File type combined with upload actionscripts/smoke-batch-verify.mjs:72 · File type combined with upload action — agent may exfiltrate local data filesconsole.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.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/lib/smoke-client.mjs:75 · npx invocation of non-well-known package — may execute untrusted codelabel: `npx -y ${options.packageSpec}`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈53 tok
1 file · 57 in bundle
Tool list per prompt
≈7,112 tok
45 tools · 158 per tool
Handshake
1430 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 178

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%
  1. 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.
  2. 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.
  3. 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.
  4. Collects environment variables by secret-like names≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  5. 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.
  6. 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.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim oliveramesPropose a patch to the maintainer