attio-mcp@1.7.0
CAUTION· not startedPublisher claims: "AI-powered access to Attio CRM. Manage contacts, companies, deals, tasks, and notes. Search records, update pipelines, and automate workflows for sales and GTM teams." 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
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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: Caution 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
ATTIO_ACCESS_TOKENATTIO_API_KEYConfiguration, not credentials: ATTIO_API_BASE_URL, ATTIO_BASE_URL, ATTIO_MCP_TOOL_MODE, ATTIO_PHONE_METADATA, ATTIO_WORKSPACE_ID, COUNT_MODEL_DEFAULT, E2E_MODE, LOG_FORMAT, MCP_LOG_LEVEL, MCP_SERVER_MODE, OFFLINE_MODE, TASKS_DEBUG, USE_MOCK_DATA, VERBOSE_TESTS, VITEST- Where it talks to
- attio.com (its own)
- What we saw when it ran
- 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. It asks for ATTIO_ACCESS_TOKEN, ATTIO_API_KEY and talks to attio.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-21 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Collapsed <details> block carrying instructions; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 16 s · 3 scenarios · 0 deviationsStatic findings
// Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><strong>Building from Source</strong></summary> For development or custom deployments: ```bash git clone https://github.com/kesslerio/attio-mcp-server.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.const envPath = path.resolve(process.cwd(), '.env');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.**🎉 v1.0.0 Milestone**: Complete Attio CRM surface coverage with full ChatGPT Developer Mode integration.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.## 🚀 **ChatGPT Developer Mode Integration**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."test:e2e": "node --env-file=.env test/e2e/run-e2e-tests.js",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."test-hooks": "chmod +x build/test-hooks.sh && ./build/test-hooks.sh",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- **📖 Setup Guide**: See [ChatGPT Developer Mode docs](./docs/chatgpt-developer-mode.md) and [Cloudflare Worker Guide](./examples/cloudflare-mcp-server/README.md)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."postbuild": "shx chmod +x dist/*.js && shx mkdir -p dist/templates && shx cp -r src/templates/* dist/templates/",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.**🎉 v1.0.0 Milestone**: Complete Attio CRM surface coverage with full ChatGPT Developer Mode integration.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."test:e2e:tools": "node --env-file=.env ./node_modules/vitest/vitest.mjs run --config configs/vitest/vitest.config.e2e.ts test/e2e/tools/",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// Accept both full ISO format and date-only formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- **📖 Setup Guide**: See [ChatGPT Developer Mode docs](./docs/chatgpt-developer-mode.md) and [Cloudflare Worker Guide](./examples/cloudflare-mcp-server/README.md)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.## 🚀 **ChatGPT Developer Mode Integration**Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."test:e2e:limited": "node --env-file=.env test/e2e/run-e2e-tests.js --limited",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// Environment variables will need to be set manually if .env loading failsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."test:e2e:check": "node --env-file=.env test/e2e/run-e2e-tests.js --check",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."docker:build": "chmod +x scripts/docker-build.sh && ./scripts/docker-build.sh",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- **Developer Mode Ready**: Every tool now publishes MCP safety annotations (`readOnlyHint`, `destructiveHint`) so OpenAI Developer Mode can auto-approve reads and request confirmation for writes.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- **Developer Mode Ready**: Every tool now publishes MCP safety annotations (`readOnlyHint`, `destructiveHint`) so OpenAI Developer Mode can auto-approve reads and request confirmation for writes.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."setup:minimal": "chmod +x scripts/setup-dev-env.sh && ./scripts/setup-dev-env.sh --skip-tdd --skip-ide --skip-hooks",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."test:e2e:help": "node --env-file=.env test/e2e/run-e2e-tests.js --help",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."setup": "chmod +x scripts/setup-dev-env.sh && ./scripts/setup-dev-env.sh",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 attio-mcp@1.7.0 as of 37 min ago. This is the package itself, not its dependencies.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim kesslerio: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- 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.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.