Skills/npm/affine-mcp-server

affine-mcp-server@3.12.0

VERIFIED· install only

Publisher claims: "Model Context Protocol server for AFFiNE - enables AI assistants to interact with AFFiNE workspaces, documents, and collaboration features." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher dawncr0w · publishing for 424 daysInstalls 3,797Last detonated 5d ago
$claude mcp add affine-mcp-server -- npx -y affine-mcp-server
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
AFFINE_API_TOKENAFFINE_MCP_AUTH_MODEAFFINE_MCP_HTTP_ALLOW_QUERY_TOKENAFFINE_MCP_HTTP_ALLOW_UNAUTHENTICATEDAFFINE_MCP_HTTP_TOKENAFFINE_OAUTH_ISSUER_URLAFFINE_OAUTH_SCOPESAFFINE_PASSWORD or --save-credentialsConfiguration, not credentials: AFFINE_ALLOW_INSECURE_HTTP, AFFINE_BASE_URL, AFFINE_BLOB_UPLOAD_FILE_ROOTS, AFFINE_BLOB_UPLOAD_MAX_BYTES, AFFINE_BLOB_UPLOAD_RESPONSE_MAX_BYTES, AFFINE_BLOB_UPLOAD_TIMEOUT_MS, AFFINE_CLIENT_VERSION, AFFINE_COOKIE, AFFINE_DISABLED_GROUPS, AFFINE_DISABLED_TOOLS, AFFINE_EMAIL, AFFINE_GRAPHQL_PATH, AFFINE_HEADERS_JSON, AFFINE_LOGIN_AT_START, AFFINE_MCP_HTTP_BODY_LIMIT, AFFINE_MCP_HTTP_MAX_SESSIONS, AFFINE_MCP_HTTP_PROXY_TIMEOUT_MS, AFFINE_MCP_HTTP_PROXY_URL, AFFINE_MCP_HTTP_SESSION_IDLE_TIMEOUT_MS, AFFINE_MCP_HTTP_SHUTDOWN_TIMEOUT_MS, AFFINE_MCP_PUBLIC_BASE_URL, AFFINE_TOOL_PROFILE, AFFINE_WORKSPACE_ID, AFFINE_WS_ACK_TIMEOUT_MS, AFFINE_WS_CLIENT_VERSION, AFFINE_WS_CONNECT_TIMEOUT_MS
Where it talks to
affine.pro (its own)Also proxy.internal — 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
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names proxy.internal as well as its own vendor. The guard injects AFFINE_API_TOKEN, AFFINE_MCP_AUTH_MODE, AFFINE_MCP_HTTP_ALLOW_QUERY_TOKEN, AFFINE_MCP_HTTP_ALLOW_UNAUTHENTICATED, AFFINE_MCP_HTTP_TOKEN, AFFINE_OAUTH_ISSUER_URL, AFFINE_OAUTH_SCOPES, AFFINE_PASSWORD only into requests to affine.pro (and its subdomains) and refuses the rest.

$vet-skills run --secrets AFFINE_API_TOKEN=affine.pro,AFFINE_MCP_AUTH_MODE=affine.pro,AFFINE_MCP_HTTP_ALLOW_QUERY_TOKEN=affine.pro,AFFINE_MCP_HTTP_ALLOW_UNAUTHENTICATED=affine.pro,AFFINE_MCP_HTTP_TOKEN=affine.pro,AFFINE_OAUTH_ISSUER_URL=affine.pro,AFFINE_OAUTH_SCOPES=affine.pro,AFFINE_PASSWORD=affine.pro -- npx -y affine-mcp-server

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-10 and scored it 91/100 (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 · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Authorization escalation languagedocs/configuration-and-deployment.md:558 · Authorization escalation language · informational: not an instruction file…p doctor --json` - `doctor` also checks selected-workspace membership, realtime root access, effective tool filters, rejects an unprotected non-loopback HTTP bind, and val…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagepackage.json:84 · npx invocation of non-well-known package — may execute untrusted code"test:data-view-ui": "npx playwright test tests/playwright/verify-data-view.pw.ts --config tests/playwright/playwright.config.ts",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)dist/index.js:20 · MCP server using network transport (SSE/HTTP) — data sent over networkimport { startHttpMcpServer } from "./sse.js";Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Authorization escalation languagedocs/configuration-and-deployment.md:59 · Authorization escalation language · informational: not an instruction filemembership and realtime root access when a default workspace is configured,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagepackage.json:103 · npx invocation of non-well-known package — may execute untrusted code"test:playwright": "npx playwright test --config tests/playwright/playwright.config.ts",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languagedocs/getting-started.md:229 · Authorization escalation language · informational: not an instruction fileworkspace membership, realtime workspace-root access, effective tool filters,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageCHANGELOG.md:193 · Authorization escalation language · informational: not an instruction file- Make `doctor` validate selected-workspace membership, realtime root access, effective tool filters, HTTP exposure, and OAuth readiness before reporting success.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagepackage.json:81 · npx invocation of non-well-known package — may execute untrusted code"test:edgeless-ui": "npx playwright test tests/playwright/verify-edgeless-canvas.pw.ts --config tests/playwright/playwright.config.ts",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈74 tok
1 file · 70 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for affine-mcp-server@3.12.0 as of 5d ago. This is the package itself, not its dependencies.