Quillm MCP server
Commit Oct 29, 2026Allows AI agents to create and maintain dashboards, trackers, and decision documents that teams can access via shared links.
Also known as streamfog/quillm-plugin, quillm-plugin
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Oct 29, 2026
- License
- MIT
What is Quillm MCP?
Quillm allows AI agents to create and maintain dashboards, trackers, and decision documents that teams can access via shared links.
Summary generated from the project's README
About Quillm MCP server
Creating and maintaining shared dashboards, trackers, and decision documents for your team is what Quillm enables through AI agents. Instead of agents rewriting entire documents every time they update information, this server uses separate datasets to store numbers. This allows an agent to add new rows run after run to keep a page current without altering the existing structure. Every change is signed by the specific agent responsible, and all saves undergo a test-render before becoming visible to readers.
Developers can connect to the hosted MCP server via OAuth in a browser or by using a bearer token for headless environments like CI or cron jobs. It integrates with various clients including Claude Desktop, Claude Code, Cursor, ChatGPT, and Grok Build. Once connected, an admin can manage permissions through a workspace Agents page to limit what an agent can access or revoke its ability to make changes.
What you can do with it
- 1Maintain automated data trackersAsk an agent to update a recurring tracker by adding new data rows to a dataset without rewriting the whole page.
- 2Generate shareable team documentsHave an AI agent create a decision document and provide a link that team members can open without needing an AI account.
- 3Manage agent permissions in CIUse a bearer token to allow a scheduled job to update workspace datasets in a headless environment.
- 4Verify page layouts before publishingInstruct an agent to check how a new dashboard looks by using the test-render tool before it goes live.
Written from the project's README. Every use case is checked against a quote from it.
How to install Quillm MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Quillm MCP in Claude Code
$ claude mcp add --transport http quillm-plugin https://quillm.ai/mcpInstall Quillm MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"quillm-plugin": {
"url": "https://quillm.ai/mcp"
}
}
}Install Quillm MCP in VS Code
.vscode/mcp.json
{
"servers": {
"quillm-plugin": {
"type": "http",
"url": "https://quillm.ai/mcp"
}
}
}Install Quillm MCP in VS Code CLI
$ code --add-mcp '{"name":"quillm-plugin","type":"http","url":"https://quillm.ai/mcp"}'Install Quillm MCP in Codex
$ codex mcp add quillm-plugin --url https://quillm.ai/mcpInstall Quillm MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.quillm-plugin] url = "https://quillm.ai/mcp"
Install Quillm MCP in Gemini CLI
$ gemini mcp add -s user --transport http quillm-plugin https://quillm.ai/mcpInstall Quillm MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"quillm-plugin": {
"url": "https://quillm.ai/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablestreamfog/quillm-plugin is public and reachablegithub.com/streamfog/quillm-plugin ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-29github.com/streamfog/quillm-plugin ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubQuillm plugin
Quillm keeps the small tools your agents build for your team: dashboards, trackers, decision docs and calculators. Each page lives at one address your team opens like a doc, with no AI account needed. The numbers live in datasets apart from the page, so an agent keeps a page current by adding rows, run after run, without rewriting it. Every save is test-rendered before readers see it, every revision is kept, and every change is signed by the agent that made it.
This repository connects your agent to Quillm. It holds:
- the connection to Quillm's hosted MCP server,
https://quillm.ai/mcp, which you sign in to with OAuth in your browser; - one skill,
skills/quillm/SKILL.md, that teaches the agent the habits that keep pages useful for months, including how a scheduled agent should add each run's numbers without touching the page.
The server itself is hosted by Streamfog and is not part of this repository.
Install
| App | How |
|---|---|
| Claude Code | claude plugin marketplace add streamfog/quillm-plugin, then claude plugin install quillm@quillm. Run /mcp and choose Authenticate. |
| claude.ai, Claude Desktop, Cowork | Settings → Connectors → find Quillm in the directory, or add a custom connector with https://quillm.ai/mcp. |
| ChatGPT, Codex | Find Quillm in the plugin directory. |
| Cursor | Install Quillm from the Cursor Marketplace. |
| Grok Build | Install Quillm from the plugin marketplace. |
| Anything else that speaks MCP | Add https://quillm.ai/mcp as a remote (Streamable HTTP) server and sign in. |
Step-by-step instructions for each app: https://quillm.ai/connect
The first time a tool is used, a browser window asks you to sign in to Quillm with Google, choose a workspace (or name a new one), and decide whether the agent may change things or only read. The agent then appears on the workspace's Agents page, where an admin can limit it to some collections, sign an app out, or revoke it.
Without a browser (CI, cron, servers)
An admin can create a token for an agent on the workspace's Agents page and give it to the job directly, for example:
claude mcp add --transport http quillm https://quillm.ai/mcp --header "Authorization: Bearer qlm_…"
Keep the token in your CI's secret store, not in a repository.
What the agent can do
Read the workspace, read and write datasets, create and update pages, test-render a page, share a page by link when asked, leave notes for the next agent, and report a problem with Quillm. The full list, with what each tool reads or changes and how much context the server uses, is at https://quillm.ai/connect#tools.
Privacy
What Quillm stores and what it sends to other services is listed in the privacy policy. Workspace admins can export everything at any time.
Files
| File | For |
|---|---|
.claude-plugin/plugin.json, .claude-plugin/marketplace.json, .mcp.json |
Claude Code, claude.ai and Cowork; also read by Grok Build |
.cursor-plugin/plugin.json, mcp.json |
Cursor |
.codex-plugin/plugin.json |
ChatGPT and Codex |
.grok-plugin/plugin.json |
Grok Build |
plugin.json |
Agent Plugins (portable manifest) |
server.json |
The Official MCP Registry entry, ai.quillm/quillm |
Support
Write to kev@limelit.ai, or open an issue in this repository.
License
MIT. See LICENSE.
Quillm MCP questions
How do I add Quillm MCP to Claude Code?
Run claude mcp add --transport http quillm-plugin https://quillm.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Quillm MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do agents update data without breaking the page layout?
Agents keep pages current by adding rows to datasets instead of rewriting the entire page.
How can I use Quillm in a CI/CD or cron environment without a browser?
An admin can generate a token on the workspace's Agents page and provide it to the job via an Authorization header.
Can my team view the pages without an AI account?
Yes, each page is accessible via a unique link that anyone on your team can open like a standard document.
What level of control does an admin have over an agent?
Admins can limit an agent to specific collections, sign it out, or revoke its access entirely.