muse-glimmer-agent
Provides integration with a local Ollama instance, listing available Ollama models and running AI agents powered by Ollama-hosted models such as muse-glimmer.
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., "@muse-glimmer-agent What's the weather in Paris today?"
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.
Muse Glimmer + MCP + Langfuse (local)
A minimal Pydantic AI agent that:
runs
muse-glimmer(Meta's 30B agentic model) through a local Ollama instance,has MCP enabled: a local FastMCP server (
mcp_server.py) is attached as a stdio subprocess, exposingget_weather,get_current_time, andlist_ollama_modelsas agent tools,sends full traces (model requests, tool calls, outputs) to a local Langfuse instance for observability.
Prerequisites
Ollama running with the model pulled:
ollama pull muse-glimmerA local Langfuse instance (e.g. via
docker composefrom the Langfuse repo) reachable athttp://localhost:3000.uv (or use
python3 -m venv+pip).
Related MCP server: MCP Ollama Consult Server
Setup
cp .env.example .env # then fill in your Langfuse keys
uv sync # installs pydantic-ai, fastmcp, langfuse, ....env:
LANGFUSE_PUBLIC_KEY=pk-lf-...
LANGFUSE_SECRET_KEY=sk-lf-...
LANGFUSE_BASE_URL=http://localhost:3000
LANGFUSE_HOST=http://localhost:3000
OLLAMA_BASE_URL=http://localhost:11434/v1
OLLAMA_MODEL=muse-glimmerRun
uv run python agent.pyThe agent answers three demo prompts, calling MCP tools as needed:
š§ User: What is the weather in Paris today?
š¤ Agent: Weather in Paris: clear skies, 22°C, humidity 51%.
š§ User: What time is it in Tokyo right now?
š¤ Agent: The current time in Asia/Tokyo is 2026-08-25 21:04:33 JST.
š§ User: Which Ollama models are available locally?
š¤ Agent: NAME ID SIZE MODIFIED ...Observability (Langfuse)
Open http://localhost:3000 ā Traces. Each run produces traces named
muse-glimmer-mcp-agent, with spans for model requests (input/output tokens)
and each MCP tool call ā inspect inputs, outputs, latencies, and costs.
Expose the agent as an MCP server
agent_mcp_server.py flips the architecture around: the agent itself becomes
an MCP server exposing one tool ā ask_agent(prompt) ā to any MCP client
(Claude Desktop, VS Code, Cursor, another Pydantic AI agent, ...). Each call
runs muse-glimmer via Ollama, still has the inner MCP tools, and is traced
to Langfuse.
Run the server
uv run python agent_mcp_server.pyClient configuration
Point any MCP client at this server using your uv-managed venv's Python
(uv run --project <repo> python also works). Examples:
Claude Desktop ā claude_desktop_config.json:
{
"mcpServers": {
"muse-glimmer-agent": {
"command": "/home/d3lee/.local/bin/uv",
"args": ["run", "--project", "/home/d3lee/my-repos/pydantic-ai-mcp-server-sample", "python", "agent_mcp_server.py"]
}
}
}VS Code ā .vscode/mcp.json:
{
"servers": {
"muse-glimmer-agent": {
"type": "stdio",
"command": "uv",
"args": ["run", "--project", "/home/d3lee/my-repos/pydantic-ai-mcp-server-sample", "python", "agent_mcp_server.py"]
}
}
}Cursor ā .cursor/mcp.json:
{
"mcpServers": {
"muse-glimmer-agent": {
"command": "uv",
"args": ["run", "--project", "/home/d3lee/my-repos/pydantic-ai-mcp-server-sample", "python", "agent_mcp_server.py"]
}
}
}Layout
File | Purpose |
| Pydantic AI agent: Ollama model + MCP capability + Langfuse |
| FastMCP server (stdio) exposing the local tools |
| Exposes the agent itself as an MCP server ( |
| Langfuse + Ollama configuration |
pydantic-ai-mcp-server-sample
Available Tools
1 toolask_agentC
Ask the Muse Glimmer AI agent a question.
Inputs: prompt (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or misselection. The tool 'ask_agent' has a clearly distinct purpose as the sole entry point for questioning the agent.
The single tool name 'ask_agent' follows a consistent verb_noun pattern, aligned with its singular function. Naming is clear and predictable.
The server has only one tool, which feels thin but is appropriate for its narrow purpose of asking a question. It is not an extreme mismatch, but it borders on insufficient for broader agent workflows.
The domain is defined as asking the Muse Glimmer agent a question, and the single tool fully covers this operation. There are no obvious gaps within the stated scope.
Related MCP Connectors
Discover and call AI agents via MCP. Supports A2A agents and platform agents with async tasks.
LLM Orchestration Agent (Opentelemetry Api)
MCP-Native LLM Orchestration Agent
Lets Claude, Cursor or any MCP client build voice agents and place real phone calls.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables seamless integration between Ollama's local LLM models and MCP-compatible applications, supporting model management and chat interactions.13817 npm180AGPL 3.0
- AlicenseBqualityFmaintenanceEnables consulting with local Ollama models for reasoning from alternative viewpoints. Supports sending prompts to Ollama models and listing available models on your local Ollama instance.51MIT
- AlicenseAqualityDmaintenanceIntegrates Ollama's local AI models with MCP clients, enabling listing models, viewing model details, and asking questions to models.3MIT
- FlicenseNot gradedqualityDmaintenanceExposes system tools (disk usage, file listing) and weather information via Open-Meteo to MCP-compatible LLMs.-