Skip to main content
Glama
jaggernaut007

nexus-mcp-ci

by jaggernaut007
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to nexus-mcp-ci

Related Servers

  • codebase-memory

    H-Gelender
    A
    license
    Not graded
    quality
    B
    maintenance
    MCP server for local codebase memory: semantic indexing, hybrid search, and clean code analysis (static + LLM) with retrievable project notes, designed to run fully local on modest hardware.
    MIT

  • codesteer-atlas

    LuisCarlosLopes
    A
    license
    A
    quality
    A
    maintenance
    Local MCP server for semantic code search using Tree-sitter AST parsing, local embeddings, and hybrid search; enables indexing and querying codebases entirely offline.
    5
    MIT

  • mcp-local-rag

    damoqiongqiu
    A
    license
    A
    quality
    A
    maintenance
    A fully local RAG MCP server for semantic code search and code intelligence, using AST-level chunking and hybrid search to pinpoint functions, classes, and APIs. No cloud, no API keys, zero setup.
    16
    98 npm
    13
    MIT

  • cba

    davidgeorgehope
    F
    license
    Not graded
    quality
    D
    maintenance
    MCP server for semantic code search and explanation. Allows AI agents to search, ask questions, and manage memory about a codebase with local embeddings and LLM integration.
    -
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 10 tools

Disambiguation5/5

Each tool has a clearly distinct responsibility: index/status/health manage the index lifecycle, map/search/find_symbol/graph/explain serve different code-comprehension needs, analyze covers quality, and memory handles persistent context. Even the potentially overlapping status/health pair is explicitly differentiated by freshness vs liveness.

Naming Consistency4/5

Tool names are consistently lowercase and concise, mostly single imperative verbs. The pattern is slightly uneven because find_symbol uses verb_noun and memory is a noun rather than an action, but there are no mixed casing conventions or vague generic names.

Tool Count5/5

Ten tools is well within the ideal scope for a code-intelligence server. Each tool covers a meaningful capability without redundancy, and the count feels neither thin nor bloated.

Completeness4/5

The set covers the full workflow of indexing, monitoring, searching, navigating, analyzing, explaining, and retaining project context. Minor gaps exist—there is no explicit unindex/forget tool or a way to list all indexed codebases—but core workflows have no dead ends.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources