# Llm Mcp Client

> Access tools from MCP servers as LLM tools

- **Type:** MCP server
- **Install:** `agentstack add mcp-simonw-llm-mcp-client`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [simonw](https://agentstack.voostack.com/s/simonw)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [simonw](https://github.com/simonw)
- **Source:** https://github.com/simonw/llm-mcp-client

## Install

```sh
agentstack add mcp-simonw-llm-mcp-client
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# llm-mcp-client

[](https://pypi.org/project/llm-mcp-client/)
[](https://github.com/simonw/llm-mcp-client/releases)
[](https://github.com/simonw/llm-mcp-client/actions/workflows/test.yml)
[](https://github.com/simonw/llm-mcp-client/blob/main/LICENSE)

Access tools from MCP servers as LLM tools

## Installation

Install this plugin in the same environment as [LLM](https://llm.datasette.io/).
```bash
llm install llm-mcp-client
```
## Usage

This plugin registers a toolbox called `MCP` which connects to an [MCP](https://modelcontextprotocol.io/) server, discovers the tools it exposes and makes them available as LLM tools.

Pass the URL of an MCP server to the toolbox:

```bash
llm -T 'MCP("https://example.com/mcp")' 'Ask something that needs a tool' --td
```

The `--td` option shows details of the tool calls as they execute.

It works in `llm chat` too:

```bash
llm chat -T 'MCP("https://example.com/mcp")'
```

## Templates

You can save an MCP to a named [LLM template](https://llm.datasette.io/en/latest/templates.html) like this:
```bash
llm -T 'MCP("https://datasette.simonwillison.net/-/mcp")' --save blog
```
Now you can query it without specifying the full tool definition like this:
```bash
llm -t blog 'count entries and notes'
```

### Protocol modes

By default the client negotiates the protocol automatically. You can force a specific mode with the `mode=` argument:

```bash
# Force modern stateless MCP:
llm -T 'MCP("https://example.com/mcp", mode="stateless")' '...'
# Force the legacy initialize handshake:
llm -T 'MCP("https://example.com/mcp", mode="legacy")' '...'
```

### Tool name prefixes

If you are using tools from more than one server and their names might clash, give each server a prefix:

```bash
llm -T 'MCP("https://one.example.com/mcp", prefix="one_")' \
    -T 'MCP("https://two.example.com/mcp", prefix="two_")' '...'
```

### Python API

```python
import llm
from llm_mcp_client import MCP

model = llm.get_model("gpt-4.1-mini")
result = model.chain(
    "Ask something that needs a tool",
    tools=[MCP("https://example.com/mcp")],
).text()
```

Tool results containing MCP image or audio content are returned to the model as LLM attachments. An MCP error result raises `llm_mcp_client.MCPToolError`, which LLM passes back to the model as an error message.

## Development

To set up this plugin locally, first checkout the code. Then run the tests with `uv`:
```bash
cd llm-mcp-client
uv run pytest
```
To run LLM with your in-development plugin:
```bash
uv run llm --help
```

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [simonw](https://github.com/simonw)
- **Source:** [simonw/llm-mcp-client](https://github.com/simonw/llm-mcp-client)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-simonw-llm-mcp-client
- Seller: https://agentstack.voostack.com/s/simonw
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.