codex-local-ollama-mcp
Related Servers
Alternatives to codex-local-ollama-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityBmaintenanceEnables Google Antigravity CLI to offload token-heavy workloads to local Ollama models through MCP tools for code drafting, summarization, chunked map-reduce, and JSON extraction, reducing cloud token usage.7AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables Codex to offload bounded local analysis — repository and symbol discovery, context compression, code and diff review, test-log analysis, task triage, and second opinions — to local Ollama models over stdio MCP, with role, capability and quality gates returning uncertain work to Codex. It also records metadata to SQLite so a companion Windows tray/dashboard can show local usage.MIT
- AlicenseNot gradedqualityDmaintenanceExposes local Ollama instances as tools for Claude Code, allowing users to offload code generation, text drafting, and embedding tasks to local GPUs. It supports multi-turn conversations and model management through the Model Context Protocol.MIT
- AlicenseNot gradedqualityBmaintenanceMCP server wrapping local Ollama models for offload from API-priced orchestrators. Nine stdio tools - generation, summarisation, analysis, drafting, code tasks (docstring/test/explain/review/types/refactor-suggest), diff-driven tasks (commit-message/pr-description/changelog/summary/impact), mechanical transforms, and model management (list/pull). Apache-2.0.16 npmApache 2.0
- AlicenseAqualityBmaintenanceEnables AI agents to offload mechanical, high-token work to local Ollama models through MCP, with role-based model discovery, batch processing, and file-aware inputs.4MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude Code to delegate sub-tasks to a local Ollama model through a single tool that accepts a prompt, optional system prompt, and model name and returns the full generated response. This routes bulk or mechanical work to a free local model so Claude's own tokens are reserved for tasks that need Claude-level reasoning.407 npmMIT
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusing it with others. The tool's purpose is clearly limited to creating a labeled local draft from user text.
With a single tool, there are no naming inconsistencies to flag. However, the name 'local_text' does not follow a clear verb_noun pattern, making it impossible to infer a broader convention.
A single tool is far too few for a server with a broad name like 'codex-local-ollama-mcp'. The tool itself appears limited and trivial relative to the implied scope, creating an extreme mismatch.
The server offers only one narrow operation, with no apparent CRUD lifecycle, retrieval, or management capabilities. The domain hinted by the server name is severely underrepresented, leaving agents without essential functionality.