"Memory systems for AI agents" matching MCP servers:

Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.

Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.

MCP server for semantic code indexing using vector embeddings, enabling AI agents to maintain persistent memory of codebases through natural language queries and intelligent chunking.

AI development assistant with 36 specialized tools for memory management, code analysis, project planning, and problem-solving through natural language interactions in Korean and English.

MCP server that wraps codebase-memory-mcp to provide code indexing, search, tracing, and architecture analysis tools with automatic reindexing after source changes.

Provides AI agents with causal code memory by indexing repositories into a graph of symbols and edges, enabling context-aware retrieval of relevant code slices.

An MCP server that provides a semantic index and 14 bounded tools for AI agents to navigate Excel workbooks by symbols, references, and diagnostics, avoiding the need to read entire rows.

Provides persistent memory and semantic code understanding for AI assistants using MongoDB Atlas Vector Search. Enables intelligent code search, memory management, and pattern detection across codebases with complete semantic context preservation.

Provides long-term memory and codebase AST intelligence for AI coding agents, enabling persistent context handoff and high-efficiency symbol queries.

An MCP server that gives autonomous coding agents deterministic, schema-validated tools for EVM smart contract development — security scanning, gas profiling, compiler diagnostics, and transaction simulation.

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

Official Codna MCP server with Mojo-powered risk simulation. Maps repos with zero LLM tokens. 5 stdio tools: triage, root-cause analysis and fix plans (optional PRs), SARIF reachability proof, on-device code memory and bug reporting. Introspection needs no credentials; execution requires a one-time free codna login. Source: cli/codna/mcp_server.py. Registry: io.github.thyn-ai/codna.

Provides verified dependency-audit verdicts for AI agents, checking installed versions against OSV advisories and splitting direct vs transitive dependencies.

Enables AI agents to search Minecraft obfuscated name mappings (class, method, field) across 38 versions, aiding modding, plugin development, and reflection.

RCP-1 is an enterprise-ready MCP server that connects AI assistants to SAP ABAP systems via the ADT REST API, with built-in security, access controls, and deployment options for BTP or on-premise.

MCP server that lets AI agents search and inspect shadcn components from the encode-ui registry, returning metadata, source code, and install commands.

Local MCP server that provides DeepSeek-powered code review, file analysis, and consultation tools for coding agents, enabling read-only analysis with minimal token overhead.

Enables AI assistants to perform read-only introspection of Symfony applications, exposing routes, controllers, services, entities, database schema, migrations, logs, and more via MCP tools.

Structural memory for coding agents — 60% fewer tokens, refactor-safe, runs entirely on your machine.

Unified MCP server: hybrid search + code graph + semantic memory. 10 tools, <350MB RAM, fully local. No API keys.