Same door for humans and AI. No gatekeeper.Register →
Explorer/MCP/darthzen/ollama-code-mcp
HYBRID

ollama-code-mcp

darthzen/ollama-code-mcp

An MCP server that lets Claude Code delegate coding tasks such as code generation, review, refactoring, and test writing to a local Ollama instance running a Qwen3 model.

↗darthzen/ollama-code-mcpExternal link; availability not verifiedLicenseMIT LicenseHybrid hosting
The Newcomer
Hasn't been around long. Nothing caught our attention, but there isn't much history to go on yet.
Time indexed (3mo)
0toolsHybrid3moindexed
Checked Jul 6, 2026
The scanner shows
Not enough data to score this server yet.
First indexed Jul 6, 2026
Server Profile
⚙
Tools catalogued
0
No tools reported by this server.
☁
Hosting
Hybrid
Can run locally or remotely depending on deployment. Review the source repository.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
—
No liveness checks recorded yet.
Publisher Verification
Not listed on the Official MCP Registry.
Source repository is available for review.
↗darthzen/ollama-code-mcpExternal link; availability not verified
Environment variables (12)
MCP_HOSTstringOPTIONALdefault: 0.0.0.0
Bind host for sse/streamable-http transports.
MCP_PORTstringOPTIONALdefault: 8765
Bind port for sse/streamable-http transports.
OLLAMA_MODELstringOPTIONALdefault: qwen3:32b
Model tag to use, as shown by ollama list on the target host.
MCP_TRANSPORTstringOPTIONALdefault: stdio
stdio (spawned locally by Claude Code), sse, or streamable-http (for remote/k8s deployment).
OLLAMA_NUM_CTXstringOPTIONALdefault: 8192
Context window passed to Ollama's options.num_ctx.
Show all 12 environment variables
OLLAMA_TIMEOUTstringOPTIONALdefault: 900
Request timeout in seconds. Defaults to 15 minutes to allow large generations/refactors on modest hardware.
OLLAMA_BASE_URLstringOPTIONALdefault: http://localhost:11434
Where Ollama listens. LAN addresses and bare host:port (scheme added automatically) are supported.
OLLAMA_CONNECT_TIMEOUTstringOPTIONALdefault: 10
TCP connect timeout in seconds.
OLLAMA_MCP_ALLOWED_DIRstringOPTIONALdefault: server CWD
Base directory that file-aware tools are confined to.
OLLAMA_MCP_DEFAULT_THINKstringOPTIONALdefault: true
Default value for each tool's think parameter when the caller omits it.
OLLAMA_MCP_MAX_FILE_BYTESstringOPTIONALdefault: 1000000
Per-file size cap for server-side reads.
OLLAMA_MCP_MAX_BATCH_FILESstringOPTIONALdefault: 20
Max files processed per batch_refactor call.

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
More from darthzen
neuvector-mcp
MCP server for SUSE NeuVector container security, exposing inventory, vulnerability, compliance, event, and policy data as 72 typed tools. Read-only by default, with optional mutating toolsets behind a confirmation handshake.
fossa-mcp
Enables AI assistants to inspect FOSSA organizations and answer software composition analysis questions through a read-only MCP server.
Similar servers
Press Release
press-release MCP — wraps StupidAPIs (requires X-API-Key)
MCP Server for LimeSurvey
Enables interaction with LimeSurvey API to create and manage surveys, questions, question groups, activate surveys, and export responses through standardized MCP endpoints.
io.github.zenml-io/mcp-zenml
MCP server for ZenML - browse stacks, pipelines, runs, artifacts & trigger pipeline runs via API
Linear
Linear MCP — wraps the Linear GraphQL API (OAuth)
HAPI MCP Server
HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants
Google Docs MCP Server
Enables Claude to read, create, and update Google Docs through OAuth authentication. Deployed as a remote Next.js server on Vercel with support for multiple users and secure API key management.
Indexed from Glama · Updates nightly