RemembrallMCP
Gives AI agents persistent memory and a pre-built code dependency graph so they stop burning tokens on exploration. Two core pieces: hybrid search over decisions and patterns you've stored across sessions, and a tree-sitter powered graph that maps functions, classes, and call relationships across eight languages. Query what depends on a symbol or what breaks if you change it in under 1ms instead of spawning exploration agents. Backed by Postgres with pgvector for embeddings. The benchmarks on Click show 95% fewer tool calls when agents can ask the graph instead of grepping. Rust core, Docker Compose setup includes schema and model download. Works with Claude Code, Cursor, Codex, and any MCP client.
- GitHub stars
- 24
- tools
- 9
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Apr 10, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
remembrall_recallSearch memories - hybrid semantic + full-text with RRF fusion
Search memories - hybrid semantic + full-text with RRF fusion
No parameter schema in public metadata yet.
remembrall_storeStore decisions, patterns, knowledge with vector embeddings
Store decisions, patterns, knowledge with vector embeddings
No parameter schema in public metadata yet.
remembrall_updateUpdate an existing memory (content, summary, tags, or importance)
Update an existing memory (content, summary, tags, or importance)
No parameter schema in public metadata yet.
remembrall_deleteRemove a memory by UUID
Remove a memory by UUID
No parameter schema in public metadata yet.
remembrall_ingest_githubBulk-import merged PR descriptions from a GitHub repo
Bulk-import merged PR descriptions from a GitHub repo
No parameter schema in public metadata yet.
remembrall_ingest_docsScan a directory for markdown files and ingest them as memories
Scan a directory for markdown files and ingest them as memories
No parameter schema in public metadata yet.
remembrall_indexParse a project directory into a field-aware code graph (functions, classes, methods, and fields across 9 languages)
Parse a project directory into a field-aware code graph (functions, classes, methods, and fields across 9 languages)
No parameter schema in public metadata yet.
remembrall_impactBlast radius analysis - "what breaks if I change this?" Works on functions, classes, methods, and fields
Blast radius analysis - "what breaks if I change this?" Works on functions, classes, methods, and fields
No parameter schema in public metadata yet.
remembrall_lookup_symbolFind where a function, class, method, or field is defined across the project
Find where a function, class, method, or field is defined across the project
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
DATABASE_URL*secretPostgreSQL connection string with pgvector extension
Readme
RemembrallMCP
Whole-codebase knowledge for AI coding agents. A field-aware code graph plus persistent memory, built on Rust, Postgres + pgvector, and exposed over MCP.
The problem: AI coding agents see a few pages out of the book each session. They grep, read, and re-derive how the codebase fits together from scratch - no map of what calls what, no way to know what breaks when something changes, and no memory of decisions made in past sessions.
The solution: RemembrallMCP gives the agent the whole codebase - a field-aware dependency graph (functions, classes, methods, fields, and the references between them) across 9 languages, plus persistent memory that survives between sessions.
Details
- Repository
- github.com/cdnsteve/remembrallmcp
- Categories
- AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
- Package
remembrallmcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Yantrikdb Mcpyantrikos/yantrikdb-mcpCognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection24stars
DataSinkingheubme2020/datasinkingFull-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents.22stars
FlowState Hosteddialectforge/flowstateHosted shared memory for AI apps: project decisions, to-dos and learnings. Beta.22stars
offloadtailucanh/offload-mcp-serverHand heavy read-only work to a background agent CLI (Antigravity) and read back a short report.21stars
Octobrainmuvon/octobrainPersistent memory for AI assistants with semantic search and knowledge graph relationships.20stars
RisingWaverisingwavelabs/risingwave-mcpQuery, inspect and operate RisingWave, the PostgreSQL-compatible streaming database, from an agent.20stars