PolyAI Agent Studio MCP Server
Provides tools for accessing PolyAI Agent Studio rules, enabling AI agents to list, retrieve, search, and concatenate rules for building conversational AI applications.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
PolyAI Agent Studio MCP Server
An MCP (Model Context Protocol) server that exposes the PolyAI Agent Studio Cursor rules as tools and resources, making them available to any MCP-compatible client (Claude Desktop, Cursor, etc.).
Tools
Tool | Description |
| List all 13 available rules with descriptions and tags |
| Get the full content of a specific rule |
| Search across all rules for a keyword |
| Get all rules concatenated (full context dump) |
Related MCP server: Inky MCP Server
Available Rules
agent-studio-anti-patterns— Common mistakes and anti-patterns to avoidagent-studio-conversation-style— Natural language and conversation style guidelinesagent-studio-entities— Entity definition patternsagent-studio-flows— Flow structure, step prompts, navigationagent-studio-lifecycle-functions— start/end function patternsagent-studio-low-code-flows— Low-code flow configurationagent-studio-project-structure— Project directory layout and required filesagent-studio-state-and-metrics— State management and metrics trackingagent-studio-topics— Topic YAML format and patternsagent-studio-utterances— Utterance/example query guidelinesagent-studio-writing-functions— Python function writing patternscall-diagnostics— Call diagnostics patternscall-diagnostics-trigger— Call diagnostics trigger configuration
Running Locally
# stdio (for Claude Desktop / Cursor)
python server.py
# SSE HTTP server
MCP_TRANSPORT=sse PORT=8000 python server.pyClaude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json)
{
"mcpServers": {
"polyai-agent-studio": {
"command": "python",
"args": ["/path/to/polyai-agent-studio-mcp/server.py"],
"env": { "MCP_TRANSPORT": "stdio" }
}
}
}Remote (hosted) config
{
"mcpServers": {
"polyai-agent-studio": {
"url": "https://YOUR-RAILWAY-URL/mcp"
}
}
}Deploying to Railway
Fork / push this repo to GitHub
Go to railway.app, create a new project → Deploy from GitHub repo
Railway auto-detects the Dockerfile and deploys
Set env vars if needed (defaults work out of the box)
Your MCP server will be available at
https://<your-app>.up.railway.app/sse
Health Check
GET /healthReturns:
{"status": "ok", "rules_loaded": 13, "server": "polyai-agent-studio-mcp"}Updating Rules
Rules are stored in rules/*.md. To update:
Copy new/updated
.mdfiles intorules/Push to GitHub — Railway redeploys automatically
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP gateway for teams deploying AI tools at scale to employee-facing and headless agents.
Connect AI clients to your Dactic work context through a hosted MCP service.
Query, browse, and automate OmegaAI workspaces from any MCP client. Streamable HTTP with OAuth 2.0.
MCP gateway: one connection for your AI apps, with tool policies, PII redaction and audit logs.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceEnables programmatic control of Cursor's cloud-based AI agents for automated code generation and repository management via standardized MCP tools.6MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that connects Cursor IDE to Inky backend, enabling users to list and filter personalized coding rules stored in Pinecone.1MIT
- AlicenseAqualityDmaintenanceEnables any MCP-compatible AI tool to read and leverage Cursor's context files (rules, agents, and skills) with their activation logic, allowing teams to maintain a single source of context across different AI coding assistants.68 npmMIT
- AlicenseAqualityDmaintenanceEnables MCP clients to invoke Cursor SDK's agent runtime, run coding agents, list models, and continue conversations.41MIT