LTM MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
LTM MCP Server
An MCP server that lets any MCP-capable AI — Claude Code, Claude Desktop,
LM Studio, and (via a tunnel) cloud AIs like claude.ai and ChatGPT — search
your own local Long-Term Memory: a Postgres + pgvector corpus of your
documents, embedded with mxbai-embed-large and optionally reranked by a
local cross-encoder.
Local-only. Read-only. No secrets. The server talks to Postgres and Ollama on 127.0.0.1; the Postgres session is forced into read-only transactions, every query is a parameterized SELECT, and nothing leaves the machine unless you deliberately put a tunnel in front of it.
Why
I run a real-estate operation and got tired of my own filing system beating me: statements, leases, loan docs, taxes, email — terabytes of it, spread across decades. So I built a local "brain": every document OCR'd, extracted, chunked, and embedded into Postgres + pgvector (~100K documents in my deployment). This repo is the connective tissue — the MCP server that lets the AI tools I already use query that corpus directly, with honest confidence scores so the AI says "that isn't in the corpus" instead of guessing.
Status: in-progress, shared to show the approach. It runs daily against my corpus; the ingestion pipeline that builds the database is a separate (not yet published) project — this repo assumes you already have the tables described below.
Related MCP server: RAG In A Box MCP Server
Architecture
AI client (Claude Code / Desktop / LM Studio / cloud via tunnel)
│ MCP over stdio —or— streamable HTTP (bearer-gated)
▼
server.py
│ 1. embed query → Ollama mxbai-embed-large (query prefix)
│ 2. cosine top-50 → Postgres, emb_mxbai vector(1024) (+HNSW)
│ 3. rerank to top-k → mxbai-rerank-base-v2 (persistent worker,
▼ optional — see LTM_RERANK_*)
results + honest confidence verdictExpected schema: documents (id, root, relpath, doc_type, title, text, ...),
doc_chunks (id, doc_id, text), emb_mxbai (chunk_id, embedding
vector(1024)). An HNSW index on emb_mxbai is detected per-query — searches
work without it (sequential scan, slower) and speed up the moment it exists.
Tools
ltm_search(query, k=8, rerank=true, doc_type=null, path_contains=null)
Semantic search. Returns hits with source path, doc_type, snippet, cosine similarity, rerank_score, and a confidence verdict derived from the reranker's absolute top score:
top rerank score | verdict |
≥ 6 |
|
3 – 6 |
|
< 3 |
|
The LOW gate is real: nonsense queries score ~2.6 and get flagged, while a
query the corpus actually answers scores 10+. When a search comes back LOW,
the right behavior is "this doesn't appear to be in the corpus" — not forcing
an answer from weak hits. With rerank=false the verdict falls back to a
coarser cosine-based gate and is labeled as such.
ltm_get_document(path_or_id, max_chars=20000)
Returns a document's extracted text from the database (the ingestion text
layer, not the raw file) plus metadata. Accepts a numeric doc_id, an exact
path, or a path fragment — ambiguous fragments return a candidate list.
ltm_stats()
Corpus counts by type, chunk/embedding coverage, HNSW index status, Ollama and reranker availability, table sizes.
Quickstart (stdio, local clients)
python3 -m venv venv && venv/bin/pip install -r requirements.txt
# Claude Code:
claude mcp add ltm --scope user -- /path/to/venv/bin/python /path/to/server.py
# Claude Desktop / LM Studio — same shape in their mcpServers config:
# { "mcpServers": { "ltm": { "command": "/path/to/venv/bin/python",
# "args": ["/path/to/server.py"] } } }Prereqs: Postgres with pgvector and the schema above; Ollama running with
mxbai-embed-large pulled.
HTTP mode (remote / cloud AIs)
python server.py --http # streamable HTTP on 127.0.0.1:8322Bearer-token gated: a token is minted on first run into ~/.ltm/http-token
(0600; LTM_HTTP_TOKEN_FILE overrides). Clients send
Authorization: Bearer <token>, or — for connector UIs with no header field
(claude.ai, ChatGPT) — embed it in the URL path: https://host/t/<token>/mcp.
Access logging is disabled so the token is never logged; comparisons are
constant-time; /healthz is open and returns only "ok".
The server binds 127.0.0.1 only. Expose it exclusively through an
outbound-only tunnel (Cloudflare Tunnel, Tailscale Funnel) — never a
port-forward. Set LTM_PUBLIC_HOST to your tunnel hostname so it passes the
transport-security host check. Hookup steps for claude.ai / ChatGPT / Gemini
CLI: docs/CONNECT-CLOUD-AIS.md.
Config (env, all optional)
Variable | Default | Purpose |
| 127.0.0.1 / 5433 | Postgres |
| postgres / brain | Postgres |
| embedder | |
| mxbai-embed-large | embedding model |
| unset (rerank off) | cross-encoder worker |
| 50 | rerank pool size |
| 3 / 6 | confidence gates |
| 127.0.0.1 / 8322 | HTTP mode |
| ~/.ltm/http-token | bearer token file |
| unset | public tunnel hostname (HTTP mode) |
Security posture
Read-only by construction:
default_transaction_read_only = on; every query is a parameterized SELECT; three tools only; no SQL passthrough, no file reads, document text capped atmax_chars≤ 500K.Bearer required on everything except
/healthz. 401 otherwise.No open ports in the tunnel deployment: the server binds 127.0.0.1; the tunnel daemon makes an outbound connection to its edge.
Token hygiene: 0600 token files, access log off, secrets never printed.
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.
Analytical memory for AI agents: a real Postgres queried in plain English over MCP. One command.
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables semantic search across text documents using vector embeddings stored in PostgreSQL. Provides multiple search modalities including semantic similarity, question/answer, and style-based search through a retrieval-augmented generation system.3Apache 2.0
- FlicenseNot gradedqualityBmaintenanceEnables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.4-
- FlicenseNot gradedqualityDmaintenanceProvides read-only, citation-backed semantic search and retrieval-augmented generation over enterprise documents via standardized MCP tools, with local embeddings for privacy.-
- FlicenseNot gradedqualityBmaintenanceEnables local full-text and semantic search over saved content, providing search and retrieval capabilities via MCP for AI assistants.-