Skip to main content
Glama

Related Servers

Alternatives to knot

  • A
    license
    B
    quality
    D
    maintenance
    A complete MCP server for Retrieval-Augmented Generation with file management and vector memory for agents. Supports multiple document formats (PDF, DOCX, TXT, MD, CSV, JSON) with semantic search using Hugging Face embeddings and ChromaDB for efficient vector storage.
    11
    10 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    Turns Claude Desktop into a personal document question-answering system using local vector search. Index PDF, TXT, and Markdown documents into collections and get answers based strictly on your documents with zero hallucination.
    10 npm
    -

Related Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    A graph-powered code intelligence engine that indexes codebases into a structural knowledge graph to provide AI agents with deep context on function calls, types, and execution flows. It offers local, zero-dependency tools for hybrid search, impact analysis, and dead code detection across Python, JavaScript, and TypeScript projects.
    484 PyPI
    819
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A minimalist indexing tool that provides AI agents with semantic search and structural AST parsing for deep codebase understanding. It enables autonomous agents to navigate large codebases predictably using vector embeddings and native language server capabilities like definition and reference tracking.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI coding agents to locate code by meaning rather than text patterns, combining embedding-based semantic search, exact/regex literal matching, and tree-sitter AST structural filters to return compact, tree-shaken code context. It also supports symbol metadata filtering, duplicate detection, codebase surveys and clustering, call-graph exploration, and exhaustive changed-file audits.
    2
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides semantic code search and code insights via a knowledge graph, enabling AI to understand, navigate, and modify complex projects with deep dependency and architecture analysis.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI coding agents and developers to search code by meaning and exact text, map symbols, dependencies, blast radius and context, inspect git-change impacts, and trace live Python or JavaScript execution from a local air-gapped SQLite index.
    Apache 2.0

TDQS

A4.6/5.0

Scored across 7 tools

Disambiguation5/5

Each tool targets a distinct axis: semantic search, reverse-dependency lookup, single-file anatomy, endpoint catalogue, file listing, repo dependency graph, and repo inventory. Descriptions actively disambiguate from each other with explicit 'do NOT use this, use X instead' guidance (e.g. search_hybrid_context vs find_callers, list_files vs explore_file).

Naming Consistency4/5

All names are snake_case with a verb-first pattern (find_callers, explore_file, list_endpoints, list_files, list_repositories, list_repo_dependencies). The lone deviation is search_hybrid_context, where an adjective/noun pair is inserted into the verb_noun slot, making it the one name that doesn't parse as cleanly as the rest.

Tool Count5/5

Seven tools for a code-intelligence server is tightly scoped; each covers a distinct retrieval mode (semantic, structural, relational, inventory) with no redundant surface. Nothing feels padded or missing at the count level.

Completeness4/5

Covers discovery, navigation, reverse-dependency impact analysis, endpoint mapping, and cross-repo graphs — a coherent read-only lifecycle. The main gap is content retrieval: there is no read-file/full-text tool, so agents must fall back to their own filesystem access after explore_file returns an outline.

Maintenance

ActivityNo data
ResponsivenessOutdated data