Official Yuque MCP server that connects Claude to Yuque knowledge bases for user lookup, search, books, documents, notes, resources, and table-of-contents workflows, including read, create, and update tools over stdio with personal or group API tokens.
Yuque MCP Server can search and read content, but it also exposes create, update, and delete workflows for books, documents, notes, resources, and tables of contents., The upstream security policy recommends read-only tokens when only read access is needed., Tokens passed as CLI arguments can appear in shell history, process listings, or client logs; prefer environment variables or a secrets manager., Custom YUQUE_BASE_URL values should point only to trusted Yuque deployments and should use HTTPS for remote services., Rate limits, deleted resources, token expiration, private-deployment behavior, and Yuque API changes can affect tool results.
Privacy notes
Yuque searches, user details, book metadata, document titles, document bodies, notes, resources, TOC data, group names, repo namespaces, slugs, and private deployment URLs can be sent to the MCP client and model., Created or updated Yuque content persists in the selected knowledge base and may be visible to collaborators according to Yuque permissions., Keep YUQUE_PERSONAL_TOKEN, YUQUE_GROUP_TOKEN, YUQUE_TOKEN, and private deployment URLs out of prompts, committed config, screenshots, public issues, and shared logs.
Author
Yuque
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 3 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes, network access, third-party handling.
5 areas
SafetyGeneralYuque MCP Server can search and read content, but it also exposes create, update, and delete workflows for books, documents, notes, resources, and tables of contents.
SafetyCredentials & tokensThe upstream security policy recommends read-only tokens when only read access is needed.
SafetyCredentials & tokensTokens passed as CLI arguments can appear in shell history, process listings, or client logs; prefer environment variables or a secrets manager.
SafetyNetwork accessCustom YUQUE_BASE_URL values should point only to trusted Yuque deployments and should use HTTPS for remote services.
SafetyCredentials & tokensRate limits, deleted resources, token expiration, private-deployment behavior, and Yuque API changes can affect tool results.
PrivacyThird-party handlingYuque searches, user details, book metadata, document titles, document bodies, notes, resources, TOC data, group names, repo namespaces, slugs, and private deployment URLs can be sent to the MCP client and model.
PrivacyPermissions & scopesCreated or updated Yuque content persists in the selected knowledge base and may be visible to collaborators according to Yuque permissions.
PrivacyCredentials & tokensKeep YUQUE_PERSONAL_TOKEN, YUQUE_GROUP_TOKEN, YUQUE_TOKEN, and private deployment URLs out of prompts, committed config, screenshots, public issues, and shared logs.
Safety notes
Yuque MCP Server can search and read content, but it also exposes create, update, and delete workflows for books, documents, notes, resources, and tables of contents.
The upstream security policy recommends read-only tokens when only read access is needed.
Tokens passed as CLI arguments can appear in shell history, process listings, or client logs; prefer environment variables or a secrets manager.
Custom YUQUE_BASE_URL values should point only to trusted Yuque deployments and should use HTTPS for remote services.
Rate limits, deleted resources, token expiration, private-deployment behavior, and Yuque API changes can affect tool results.
Privacy notes
Yuque searches, user details, book metadata, document titles, document bodies, notes, resources, TOC data, group names, repo namespaces, slugs, and private deployment URLs can be sent to the MCP client and model.
Created or updated Yuque content persists in the selected knowledge base and may be visible to collaborators according to Yuque permissions.
Keep YUQUE_PERSONAL_TOKEN, YUQUE_GROUP_TOKEN, YUQUE_TOKEN, and private deployment URLs out of prompts, committed config, screenshots, public issues, and shared logs.
Prerequisites
Node.js 18 or newer and npx.
Yuque personal, group, or legacy API token with the minimum scope needed for the workflow.
Yuque Cloud account or approved private Yuque deployment base URL.
Read-only token for search and retrieval workflows whenever document or book writes are not required.
Approval before creating, updating, or deleting books, documents, notes, resources, or table-of-contents entries.
Yuque MCP Server is the official Yuque Model Context Protocol server for
connecting AI assistants to Yuque knowledge-base content. It exposes tools for
the current user, search, books, documents, notes, structured resources, and
table-of-contents workflows through a stdio MCP server.
The server uses the yuque-mcp npm package. It authenticates with a Yuque token
from an environment variable or CLI argument and defaults to the Yuque Cloud API,
with optional YUQUE_BASE_URL support for private deployments.
These sources were reviewed on 2026-06-06. Prefer the live repository,
README, npm metadata, package metadata, MCP server manifest, CLI entrypoint,
server implementation, Yuque API client, document tools, security policy, and
license file for current install commands, token options, tool behavior, base URL
support, API scope, and licensing.
Features
NPM package yuque-mcp with an executable CLI.
Stdio MCP server for local clients and install/setup helpers for multiple MCP
clients.
Yuque Cloud API support plus custom YUQUE_BASE_URL for private deployments.
Token support through YUQUE_PERSONAL_TOKEN, group or legacy token variables,
or the documented CLI token flag.
User lookup and Yuque search tools.
Book workflows for listing, reading, creating, and updating books.
Document workflows for listing, reading, creating, and updating documents,
including markdown-compatible YMD/YFM flows.
For private deployments, add YUQUE_BASE_URL with the approved Yuque API base
URL. Restart the MCP client and test with a read-only query before allowing
create or update actions.
Use Cases
Search Yuque for relevant internal or personal knowledge-base documents.
List books and documents for an approved namespace.
Read Yuque document content into a Claude session for summarization or review.
Create a new document draft in a selected Yuque book.
Update an existing document, note, resource, or table-of-contents entry after
human approval.
Connect Claude to a private Yuque deployment by setting a custom API base URL.
Safety and Privacy
Yuque MCP Server should be scoped by token permissions. Use a read-only token for
retrieval and search, and switch to a write-capable token only for approved
authoring workflows. The upstream security policy warns that the server can
create, update, and delete content in a Yuque workspace, so understand token
scope before granting access.
Knowledge-base content can be sensitive. Search queries, document bodies, notes,
book names, group names, repo namespaces, table-of-contents structure, resources,
private deployment URLs, and generated updates may appear in model context,
client logs, or transcripts. Protect Yuque tokens and avoid placing them in CLI
arguments, shell history, screenshots, public issues, or committed MCP config.
Created or updated content persists in Yuque and may be visible to collaborators.
Verify book IDs, repo namespaces, document slugs, visibility settings, and
private deployment URLs before allowing write operations.
Duplicate Check
No Yuque MCP Server, yuque/yuque-mcp-server, yuque-mcp, or dedicated Yuque
knowledge-base MCP entry was found in content/mcp, content/agents,
content/guides, or content/skills. This entry is scoped to Yuque's official
MCP server and does not duplicate general document, note-taking, or knowledge
base MCP entries.
Show that Yuque MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/yuque-mcp-server)
How it compares
Yuque MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Official Yuque MCP server that connects Claude to Yuque knowledge bases for user lookup, search, books, documents, notes, resources, and table-of-contents workflows, including read, create, and update tools over stdio with personal or group API tokens.
MCP server for connecting Claude to AFFiNE Cloud or self-hosted AFFiNE workspaces, documents, databases, comments, collections, folders, tags, notifications, blobs, access tokens, semantic page composition, templates, edgeless canvas data, and workspace organization workflows over stdio or HTTP.
Apache-licensed TypeScript MCP server for Obsidian vaults with stdio and Streamable HTTP transports, Local REST API access, note search, section-aware edits, tag/frontmatter management, path policies, and read-only controls.
Official Agentset MCP server that lets Claude retrieve cited knowledge-base results from an Agentset namespace through the `knowledge-base-retrieve` tool, with optional tenant scoping and custom tool descriptions.
✓Yuque MCP Server can search and read content, but it also exposes create, update, and delete workflows for books, documents, notes, resources, and tables of contents.
The upstream security policy recommends read-only tokens when only read access is needed.
Tokens passed as CLI arguments can appear in shell history, process listings, or client logs; prefer environment variables or a secrets manager.
Custom YUQUE_BASE_URL values should point only to trusted Yuque deployments and should use HTTPS for remote services.
Rate limits, deleted resources, token expiration, private-deployment behavior, and Yuque API changes can affect tool results.
✓The full tool surface can create, update, publish, revoke, move, replace, and delete AFFiNE workspaces, documents, folders, collections, comments, database rows, blobs, surface elements, tags, and access tokens.
Start with AFFINE_TOOL_PROFILE=read_only or disable groups such as destructive, admin, blobs, users, access_tokens, docs.database, or write when the assistant only needs discovery or reading.
HTTP mode exposes MCP endpoints and must be protected with bearer or OAuth authentication, HTTPS, allowed origins, and deployment-level access controls.
AFFiNE Cloud requires API tokens for MCP usage; avoid trying to automate email/password login against Cloud deployments.
Cookie and password-based auth can grant broad account access and should be avoided for unattended or shared deployments.
✓Cyanheads Obsidian MCP can read, list, search, create, append, patch, replace, delete, tag, and edit frontmatter in the configured vault through the Local REST API plugin.
The server defaults to full-vault access unless read paths, write paths, or read-only mode are configured.
Set `OBSIDIAN_READ_ONLY=true` for research-only workflows, then narrow writes with `OBSIDIAN_WRITE_PATHS` before allowing note edits.
Delete operations are permanent in the vault and should require human review even when the MCP host supports destructive-tool prompts.
Command-palette tools are disabled unless `OBSIDIAN_ENABLE_COMMANDS=true`; command execution can trigger opaque or destructive Obsidian plugin behavior.
Streamable HTTP deployments should use JWT or OAuth auth before being exposed beyond a trusted local machine.
✓The MCP server sends Claude's retrieval queries to the Agentset API using the configured API key and namespace.
The `knowledge-base-retrieve` tool can return up to 100 results per call and can rerank results by relevance.
Namespace and tenant selection control which indexed documents are searchable; review them before connecting a shared agent.
API keys should be scoped, rotated, and stored only in the MCP server environment or a secret manager.
Custom tool descriptions can influence when the model calls the retrieval tool, so review them before use in production workflows.
Privacy notes
✓Yuque searches, user details, book metadata, document titles, document bodies, notes, resources, TOC data, group names, repo namespaces, slugs, and private deployment URLs can be sent to the MCP client and model.
Created or updated Yuque content persists in the selected knowledge base and may be visible to collaborators according to Yuque permissions.
Keep YUQUE_PERSONAL_TOKEN, YUQUE_GROUP_TOKEN, YUQUE_TOKEN, and private deployment URLs out of prompts, committed config, screenshots, public issues, and shared logs.
✓Workspaces, document titles, document bodies, comments, tags, database schemas, database rows, edgeless canvas data, notifications, user profiles, access-token metadata, blobs, and exported markdown can be sent to the MCP client and model.
API tokens, cookies, passwords, bearer tokens, OAuth config, and saved config files should be treated as secrets and kept out of prompts, logs, screenshots, issues, and committed MCP config.
Generated or modified documents can persist in AFFiNE and may become visible to collaborators depending on workspace permissions and sharing state.
Blob upload, cleanup, export, and publish/revoke workflows can expose files, generated content, or collaboration state beyond the current prompt.
✓Vault notes, headings, block references, frontmatter, tags, file metadata, outgoing links, search queries, command names, plugin status, and edit history may be exposed to the MCP client and model provider.
API keys, local plugin endpoints, HTTP auth settings, path allowlists, logs, OpenTelemetry traces, and Docker environment variables can reveal private vault structure or credentials.
Tag listing is vault-wide in upstream behavior and can reveal tag names outside narrowed read paths.
Notes may contain personal journals, client work, credentials, meeting notes, research plans, health data, or other sensitive knowledge-base content.
✓Retrieved chunks can include private documents, product specs, policies, support content, internal procedures, historical project information, or customer-specific data.
Retrieval queries, namespace IDs, tenant IDs, document chunks, citations, and tool outputs may be visible to the MCP client, model provider, Agentset logs, and application telemetry.
Tenant IDs are useful for data segregation, but incorrect tenant or namespace configuration can expose the wrong knowledge base.
Do not paste API keys, namespace IDs, tenant IDs, or retrieved private chunks into shared issue reports, screenshots, or repository files.
Prerequisites
Node.js 18 or newer and npx.
Yuque personal, group, or legacy API token with the minimum scope needed for the workflow.
Yuque Cloud account or approved private Yuque deployment base URL.
Read-only token for search and retrieval workflows whenever document or book writes are not required.
Node.js and npm for installing the affine-mcp-server package.
AFFiNE Cloud API token or approved self-hosted AFFiNE credentials.
AFFiNE base URL for the Cloud or self-hosted deployment.
Clear workspace scope and least-privilege tool profile before enabling write, admin, destructive, blob, or access-token tools.
Node.js 24 or newer, or Bun 1.3.11 or newer.
Obsidian vault with the Obsidian Local REST API community plugin enabled.
Local REST API key stored in the MCP client environment.
Stdio MCP client, or reviewed Streamable HTTP deployment with authentication.
Agentset account or self-hosted Agentset deployment with a populated namespace.
Agentset API key with access to the namespace Claude should query.
Node.js 18.17 or newer for running the `@agentset/mcp` package.
Namespace ID selected with `--ns` or `AGENTSET_NAMESPACE_ID`.
Install
npx -y yuque-mcp
npm i -g affine-mcp-server
npx -y obsidian-mcp-server@latest
Run `npx @agentset/mcp --ns <namespace-id>` with `AGENTSET_API_KEY` set in the MCP server environment.