OllamaSAFE
Query model running with Ollama from within Claude Desktop or other MCP clients
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server for integrating Ollama with Claude Desktop or other MCP clients.
Requirements
- Python 3.10 or higher
- Ollama installed and running (https://ollama.com/download)
- At least one model pulled with Ollama (e.g.,
ollama pull llama2)
Configure Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"ollama": {
"command": "uvx",
"args": [
"mcp-ollama"
]
}
}
}Development
Install in development mode:
git clone https://github.com/yourusername/mcp-ollama.git cd mcp-ollama uv sync
Test with MCP Inspector:
mcp dev src/mcp_ollama/server.py
Features
The server provides four main tools:
list_models- List all downloaded Ollama modelsshow_model- Get detailed information about a specific modelask_model- Ask a question to a specified model
License
MIT
f0077448957dOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-ollama -- uvx mcp-ollama
{
"mcpServers": {
"mcp-ollama": {
"command": "uvx",
"args": [
"mcp-ollama"
]
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ask_model | read | Ask a question to a specific Ollama model |
list_models | read | List all downloaded Ollama models |
show_model | read | Get detailed information about a specific model |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
DEFAULT_URL = os.environ.get("OLLAMA_HOST", "http://127.0.0.1:11434")Gates applied: no_behavioural_pass.
f0077448957dfull audit observations/trust-audit/mcp-server/emgeee__ollama-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | f0077448957d | SAFE | B | 89 | first audit |
Questions
What is the Ollama MCP server?
Query model running with Ollama from within Claude Desktop or other MCP clients
What tools does Ollama expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Ollama safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Ollama need?
No credential environment variables were found in its source, so it appears to need none.
How does Ollama run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-ollama.
How current is this page?
The grade is for one exact copy of the source (f0077448957d), read on 2026-10-08. The repository is watched and re-audited when it changes.