Skip to main content
Glama
Shaing

ollama-agent

by Shaing
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to ollama-agent

No user-submitted related servers found.

    Related Servers

    • claude-token-saver-mcp

      BlackFoil
      A
      license
      A
      quality
      C
      maintenance
      Enables Claude Code to offload routine code generation and text processing tasks to a local Ollama LLM, saving Cloud API tokens and costs with automatic model selection and security features.
      11
      35 npm
      4
      Apache 2.0

    • Ollama MCP Server

      Jadael
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables Claude to delegate coding tasks to local Ollama models, reducing API token usage by up to 98.75% while leveraging local compute resources. Supports code generation, review, refactoring, and file analysis with Claude providing oversight and quality assurance.
      358 npm
      25
      AGPL 3.0

    • Ollama MCP Server

      JMRussas
      A
      license
      Not graded
      quality
      D
      maintenance
      Exposes 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

    • localagents

      ccebelenski
      A
      license
      A
      quality
      C
      maintenance
      Enables Claude Code to delegate agent tasks to local LLMs via llama.cpp or vLLM servers on your own hardware, reducing API usage while maintaining full agent capabilities.
      11
      10
      MIT

    • Ollama MCP Server

      ngc-shj
      A
      license
      Not graded
      quality
      D
      maintenance
      A bridge that enables Claude Code to interact with local Ollama instances for text generation, multi-turn chat, and vision-based analysis. It supports model management tasks such as listing, pulling, and showing details, alongside generating text embeddings.
      358 npm
      1
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.4/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct operation: delegated generation, diff review, summarization, index building, semantic search, and model status. Even where multiple tools invoke local models, the descriptions explicitly separate use cases, so an agent is unlikely to misselect.

    Naming Consistency4/5

    Most tool names follow a clear verb_noun pattern (delegate_task, review_diff, index_codebase, search_code). summarize is a lone single-verb name and local_models_status is a noun phrase, but these are minor deviations that do not cause confusion.

    Tool Count5/5

    Six tools is well-scoped for a local-model assistive agent. Each tool earns its place and covers a distinct utility without redundancy or bloat.

    Completeness4/5

    The tool surface covers the main local-model workflows: task delegation, diff review, large-content summarization, semantic code indexing/search, and status checks. Minor gaps exist, such as no exact-match search or model management beyond status, but these are workable and do not block the core purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources