"Using Cline as a Knowledge Graph for Coding" matching MCP servers:

An improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

tailtest-cline is a Cline plugin that automatically generates and runs tests every time the agent edits a source file. https://github.com/avansaber/tailtest-cline

An MCP server for tracking student learning via a knowledge graph, with spaced repetition scheduling and intelligent queries to identify gaps, misconceptions, and optimal next steps.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables searching Google's Knowledge Graph for real-world entities via two tools: search by query or lookup by Machine ID, returning structured data including entity types, descriptions, and URLs.

Provides LLM clients with a persistent, scalable knowledge graph memory system that supports semantic retrieval, contextual recall, and temporal awareness.

Enables building and querying vector-based knowledge graphs with node and edge management and semantic search.

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.

A Model Context Protocol server that provides persistent project context management for AI-assisted development, specifically designed for the Cline VSCode Extension.

A lean, local knowledge graph that joins a repo's code to its aSPARK delivery artifacts, enabling agents to trace user stories to code and assess impact of changes, served over MCP.

Enables MCP clients to run Cline CLI prompts and isolated repository-wide analyses, returning terminal text responses with model, duration, and usage/cost.

MCP server for coding-os, a cognitive operating system that gives AI agents memory, structure, and discipline. It exposes tools for project management, task tracking, knowledge graphs, and cognition traces to Claude Code and Codex.

Enables grounded, dated research from a curated AI-knowledge repository, offering free BM25 retrieval and a research loop that combines the knowledge base, curated sources, and the open web with tiered citations.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

Deterministic SNAP eligibility logic, exposed as auditable Model Context Protocol tools. An AI agent can read, reason, and orchestrate, but the eligibility determination itself is made by versioned, tested, cited code that a caseworker, an auditor, or a court can inspect.

Self-hosted personal knowledge graph for Claude that persists across sessions, devices, and tools. Built on Neo4j with local semantic embeddings; OAuth 2.1 lets Claude Code, Claude Desktop, and claude.ai web all hit the same graph.

Exposes a Neo4j knowledge-graph index over personal markdown notes to LLM agents via MCP, enabling semantic search, tag navigation, and relationship discovery.

An MCP server that guides AI assistants to navigate documentation using their built-in tools (grep, file reading) instead of traditional RAG.

Enables Codex to delegate review and implementation tasks to the local Qoder CN CLI as background jobs, with two permission tiers and polling-based status updates.

A server providing programming guidelines and coding standards for multiple languages, enabling access and search of best practices for C#, Go, JavaScript, Python, and TypeScript.

Indexes a mono-repo into a knowledge graph and provides MCP tools to query code structure—packages, components, routes, HTTP calls—without file reads or grep round-trips.

Exposes the local Claude Code CLI as a subagent for Codex, enabling background review and implementation jobs with two fixed permission tiers.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Delegates work from MCP clients (like Claude Code) to the Codex CLI, allowing spawning of autonomous Codex subagents for tasks.

Exposes a dependency graph of strategic sourcing artifacts and analyses as an MCP server, enabling navigation of phases, analyses, deliverables, and graph traversal for impact analysis and build order.

Enables cross-session memory and recall for AI coding assistants through a git-synced knowledge base, hybrid semantic and TF-IDF search across tool transcripts, and automatic distillation of insights with secrets scrubbing.

Provides a SQLite-backed MCP server that records agent memory as history, enabling explicit consolidation, source checks, revisions, narrative versions, and accountable forgetting.

Enables querying of a fictional CRM knowledge graph of enterprise accounts and their contacts, with tools for listing, searching, retrieving full record details, and running read-only SPARQL queries. Clients such as Claude, ChatGPT, or Adobe Coworker can connect over remote HTTP or local stdio, optionally protected by OAuth.

Exposes product-style completion tools (OpenAI chat-completions-shaped and Anthropic messages-shaped) that are fulfilled by sampling the host agent's own LLM over MCP, so no model API keys are ever needed. Also offers a model listing endpoint aliasing the host's model.

Enables AI assistants to perform intelligent semantic code search across codebases using local AI embeddings for meaning-based retrieval.

Enables supervising and orchestrating local coding agents like Muse and AGY through a client-agnostic MCP interface, with isolated Git worktrees, safe execution, and deterministic verification.

Bridges a remote, cloud-hosted agent to your local machine, exposing Pi's coding tools (read, write, edit, ls, grep, find, bash, powershell) rooted at a directory you choose. It also adds a human channel so the agent can message, question, and wait on you through tool calls instead of a platform chat UI, with OAuth 2.1 or bearer-token authorization and no persistence between runs.

A self-hosted, MIT-licensed MCP server that securely connects private documents and markdown files to LLMs. It provides a lightweight, local-first RAG infrastructure compatible with any MCP-enabled AI client or framework.

Local knowledge engine for codebases with hybrid search, knowledge graph, and interaction tracking, enabling Claude Code to search and interact with project knowledge locally.

Long-term memory for AI agents. Compiles conversations into a structured knowledge base with Claim/Evidence model, source provenance, append-only timeline, and contradiction detection. Multi-path retrieval (Exact + BM25 + Graph + weighted RRF + reranker) — 96.6% R@5 on LongMemEval-S, zero vector dependencies.

Vendor-neutral MCP server for knowledge retrieval across repositories, offering stable tools for searching, getting, and listing documents with hybrid lexical and optional semantic search.

Local-first memory for Claude Code and any MCP client: hybrid vector + keyword search and a bi-temporal knowledge graph in one SQLite file. Local embeddings, no API key, $0/token.

Lets an AI assistant search, read, and write notes and sources in your self-hosted Open Notebook, with approval-gated writes and no data sent anywhere else. It bundles tools, prompts, and skills for meeting notes, decision records, weekly reviews, and source-cited research.

A knowledge base MCP server that aggregates team knowledge from multiple sources into Postgres. It provides hybrid search (full-text + vector + RRF) via MCP tools, and enables direct recording of decisions, learnings, and pitfalls.