Fuseki MCP server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fuseki MCP serverCall server_info to verify the connection and list available tools."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Fuseki agent plugin
Connects your coding agent to the Fuseki MCP server at https://mcp.fuseki.dev — project
data, tenant-scoped, under your own permissions rather than a service account's.
This repository is generated. Every file in it is build output from the Fuseki monorepo. Edits here are overwritten by the next publish; open a change against the source instead.
Install
Claude Code:
/plugin marketplace add razvanpiticas/fuseki-plugin
/plugin install fuseki@fuseki-pluginsCodex:
codex plugin marketplace add razvanpiticas/fuseki-plugin
codex plugin add fuseki@fuseki-pluginsCursor, Gemini CLI, OpenCode, OpenClaw, Hermes — run this in your project:
pnpm dlx github:razvanpiticas/fuseki-plugin installIt detects which of those harnesses you have, writes the skill and the server declaration, and prints anything it will not write for you.
Any other MCP client: add https://mcp.fuseki.dev/mcp and set the OAuth client id to
fuseki-agent-client.
Related MCP server: yandex-mcp
After installing
Sign in when prompted, then ask your agent to call the server_info tool. It answers with the
deployment name and the tools it publishes, and it touches nothing else — so it is the one call
worth making first when something is not working.
Access is granted on Fuseki's own roles screen, per tenant: mcp:tools.read and mcp:tools.write.
Reads working while writes answer 403 means the write permission has not been granted, or the
token predates the grant.
Version 0.7.0+892e147f52e6.
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect AI agents to Filepad workspaces through OAuth MCP.
Context and control for any AI. Agent identity, scoped access, and proof across tools.
- FullmaktOAuthai.fullmakt
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
User-owned files and explicit AI Memories for authorized assistants with scoped access.
Related MCP Servers
- -licenseNot gradedqualityDmaintenanceEnables AI assistants to read and send messages in Google Chat spaces using service account authentication.-
- AlicenseNot gradedqualityFmaintenanceEnables LLM agents to interact with Yandex Tracker (and future Yandex services) using per-user credentials instead of a shared org-wide token, supporting both single-user and multi-user modes.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to access registered resources based on a fixed subject identity, enforcing default-deny policies and auditing for controlled context sharing.Apache 2.0
- AlicenseBqualityBmaintenanceEnables AI agents to access and manage Google Analytics and Google Tag Manager using the user's own Google account via the JP Agent Tracking Bridge, supporting GTM read/write/publish and GA4 read-only operations with session-bound security.24MIT