Collie
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., "@Colliescreen the first 100 titles and abstracts for inclusion"
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.
What it is
Collie is a workbench for systematic reviews and meta-analyses: protocol, search, deduplication, screening, data extraction, risk of bias, meta-analysis, GRADE and PRISMA, in one place. This kit connects the AI agent you already use to your Collie account over the Model Context Protocol (MCP). The AI runs on your own AI subscription, not on Collie. Your agent works through the same tools you see in the app: it writes suggestions and drafts, and you accept or dismiss them in Collie.
Related MCP server: Cochrane MCP
Requirements
A Collie account. Every plan can connect an agent, Free included. Sign up.
Node.js 20 or newer.
An MCP client: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, Perplexity (Mac app) or any client that runs stdio MCP servers.
Install in Claude Code (recommended)
Claude Code gets the full kit: the MCP server, skills, subagents, hooks and the live Collie pane.
/plugin marketplace add leandromedeirosfelix/collie-agent-kit
/plugin install collie@collie-agent-kitRestart Claude Code.
Ask: "Connect to Collie." The agent shows a link and a short code.
Open app.colliesr.com/connect, sign in and type the code to approve the agent. A link alone never approves it.
Type
/collieto open the Collie pane.
Details: docs/install-claude-code.md.
Manual install (other MCP clients)
The server runs with npx -y github:leandromedeirosfelix/collie-agent-kit. Add it to your client's config, restart the client, then ask the agent to connect to Collie.
Settings › Developer › Edit Config opens claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"collie": {
"command": "npx",
"args": ["-y", "github:leandromedeirosfelix/collie-agent-kit"]
}
}
}Quit Claude Desktop completely and open it again.
~/.codex/config.toml (shared by the Codex CLI, app and IDE extension):
[mcp_servers.collie]
command = "npx"
args = ["-y", "github:leandromedeirosfelix/collie-agent-kit"]
startup_timeout_sec = 60
tool_timeout_sec = 300Or: codex mcp add collie -- npx -y github:leandromedeirosfelix/collie-agent-kit. The longer timeouts cover the first download and analyses that take a few minutes.
~/.gemini/settings.json (or .gemini/settings.json in a project):
{
"mcpServers": {
"collie": {
"command": "npx",
"args": ["-y", "github:leandromedeirosfelix/collie-agent-kit"]
}
}
}~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):
{
"mcpServers": {
"collie": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:leandromedeirosfelix/collie-agent-kit"]
}
}
}Perplexity runs local MCP servers in its Mac app only.
Open Plugins and install the helper app PerplexityXPC.
Plugins › Add custom › Simple: server name
collie, commandnpx -y github:leandromedeirosfelix/collie-agent-kit.Wait until the connector shows Running, then turn on
collieunder Sources.
Field | Value |
Command |
|
Arguments |
|
Transport | stdio |
Environment | optional, see below |
Windows: if your client cannot start npx directly, use "command": "cmd" and "args": ["/c", "npx", "-y", "github:leandromedeirosfelix/collie-agent-kit"].
Optional environment variables
Variable | Default | Use |
| none | A personal access token from Collie › Settings › AI agents (MCP). Replaces the code sign-in. |
|
| The Collie address. Leave it unset. |
All clients, step by step: docs/install-manual.md.
What you get
Part | What it does | Where |
MCP server | Collie's tools for your agent: reviews, protocol, search, duplicates, screening, full text, extraction, risk of bias, analysis, GRADE, PRISMA | Every client |
13 skills | One per stage of a review, plus help. Start with | Claude Code |
8 subagents | Methodologist, search strategist, screener, extractor, risk-of-bias assessor, biostatistician, manuscript writer, peer reviewer | Claude Code |
Live pane |
| Claude Code |
Guardrail hooks | Ask you before the agent casts a real screening vote or installs R packages; check the syntax of | Claude Code |
Skills and subagents are short stubs. Each one asks Collie for its full instructions with the collie_guide tool, which answers only for a signed-in account.
Using it
Ask in plain words, for example:
"Where is my review and what's next?"
"Is a meta-analysis on early mobilisation after hip fracture surgery viable?"
"Pre-screen the next 50 records against my criteria."
"Extract the outcome data for the included studies."
"Draft the risk-of-bias assessments for the included trials."
The agent writes suggestions and drafts. You accept, edit or dismiss them in Collie. A screening vote by the agent is a real reviewer vote, so Claude Code asks you first.
Privacy and security
The kit talks only to
app.colliesr.com(or yourMSR_URL), with your token. Nothing else is sent anywhere.Your AI client sends what the agent reads to your AI provider, under your agreement with that provider.
The token is stored on your computer:
%APPDATA%\collie\token.jsonon Windows,~/.config/collie/token.jsonon macOS and Linux (readable by your user only on macOS and Linux).Disconnect this computer: ask the agent to run
collie_disconnect. Revoke the token itself: Collie › Settings › AI agents (MCP).No token can delete anything in Collie.
The kit contains no review method. Collie serves its guides to signed-in users.
More: docs/security.md.
Updating
Claude Code:
/plugin marketplace update collie-agent-kit, then restart Claude Code.Other clients:
npxfetches the kit from GitHub when the client starts the server. Restart the client. If an older version keeps running, see troubleshooting.
Uninstall
Claude Code:
/plugin uninstall collie@collie-agent-kit, then/plugin marketplace remove collie-agent-kit.Other clients: remove the
collieentry from the client's config.Then delete the token file above (or run
collie_disconnectfirst) and revoke the token in Collie › Settings › AI agents (MCP).
Troubleshooting
Problem | What to do |
"Not connected to Collie" | Ask the agent to connect, then type the code at app.colliesr.com/connect. |
The code expired, or the token was revoked | Ask the agent to run |
| Install Node.js 20+, restart the client. On Windows, try |
Behind a corporate proxy | See troubleshooting. |
Full list: docs/troubleshooting.md.
For developers
The developer documentation covers how the kit works and how to build on it:
Architecture: the server, the plugin layers, what runs where, and the human-in-the-loop guarantees.
Authentication: the code sign-in, tokens, scopes and revoking.
Tools reference: every MCP tool with its parameters, generated from the server.
Integrating other clients: any stdio MCP client, or your own TypeScript or Python code.
Contributions are welcome: see CONTRIBUTING.md. Report vulnerabilities privately as SECURITY.md describes.
Support
Write to contact@colliesr.com.
License
The agent kit is open source under the MIT License. Copyright (c) 2026 CollieSR Company. Open-source components in the server bundle: THIRD-PARTY-NOTICES.md.
The Collie service (app.colliesr.com) and the method guides it serves through collie_guide are not part of the kit. They are governed by Collie's Terms of Use.
This server cannot be deployed
Maintenance
Related MCP Connectors
Source-traced evidence research for AI agents. We organise the evidence; you decide.
Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.
Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.
Checks AI-written references against Crossref, PubMed and OpenAlex. Formats citations, PRISMA.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI-assisted meta-analysis workflows following Cochrane methodological standards, including importing RevMan data, validation, meta-analysis, forest plots, publication bias assessment, and report generation.61MIT
- AlicenseNot gradedqualityDmaintenanceTurns the Cochrane Library into a tool for AI agents to search and retrieve clinical evidence, including systematic reviews, trials, and plain-language summaries.16 npm1MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to search registered systematic review protocols, look up individual CRD records, explore the MeSH vocabulary, check for possibly duplicate/overlapping reviews, and export results in RIS format.-
- AlicenseNot gradedqualityAmaintenanceEnables an AI assistant to run systematic review screening steps such as creating projects, importing records, scoring and ranking them with a zero-shot LLM classifier, presenting records for human decisions, applying a statistical stopping criterion, and exporting results. Human reviewers retain responsibility for inclusion decisions, with probabilities hidden unless requested.Apache 2.0