"How to Read an Excel File" matching MCP servers:

A read-only MCP server that provides document awareness for agents by parsing local files into structured profiles, blocks, chunks, and search results, enabling agents to understand and cite document content without dealing with raw file formats.

An MCP server that allows Claude and other LLMs to manage persistent memories across conversations through text file storage, enabling commands to add, search, delete and list memory entries.

Metis gives AI agents expert know-how that named reviewers have approved, and only where its recorded conditions match the situation. High-risk situations go to a person. When an agent sees practice depart from procedure, it can send the expert one short question. Every retrieval is recorded on a hash-linked evidence chain.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

coldstart gives coding agents durable memory of a specific codebase, with no embeddings, no vector store, and no API key. Agents write notes after real tasks — what a file is for, how a flow spans files, which invariants hold — and those notes are surfaced automatically to a later session whose task matches, so nothing gets rediscovered from scratch. Every note is anchored to real files by content

Seven-layer agent memory over MCP. zenbrain_store routes each memory itself: steps to a procedure, emotional weight to an episode, high confidence to a pinned core memory, the rest to a semantic fact. zenbrain_recall returns each result with its id and layer; zenbrain_forget deletes one memory by both; zenbrain_consolidate runs one sleep-like pass. Local SQLite file, no account, no network call.

Read-only MCP access to the p-e relay store: an append-only corpus of provenance-bearing coordination records, with tools to fetch a record by id, list records and replies, and check existence. This image serves a snapshot frozen at build time; append_relay is listed but refused, and deposits to the live store require an HMAC-signed request.

Self-improving, verifiable memory for AI coding agents. Learns how you work, stops repeating mistakes, models each project, recalls the right lesson at the right moment. Every memory is signed and tamper-evident. Local-first.

Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.

Local-first external brain for Claude Code, Codex, and any MCP client. Stores decisions, entities, and session artifacts in one SQLite file and exposes MCP tools for recall, page, promote, review, graph-query, and source-status.

An MCP server for reading, creating, and managing PDF, DOCX, and Excel documents with OCR, styling, categorization, and remote file bridges.

Provides an AI agent with a searchable markdown notes vault, offering tools to create, read, list, search, update, and delete notes stored as plain .md files.

An MCP server that enables LLMs to pull-based search through Clawket's RAG repository for exploratory and conditional queries. It provides read-only access to search artifacts, tasks, and decisions via HTTP API.

Multi-user, file-backed MCP memory server enabling isolated namespaces and persistent memory across sessions and AI clients.

An MCP server that provides AI agents with a persistent, PostgreSQL-backed virtual filesystem, supporting session-isolated file operations, cross-session shared stores, and glob/grep search.

An MCP server that records decisions, rejected alternatives, and justifications, and retrieves them later to avoid re-litigating past choices. It stores data locally in SQLite and Markdown.

Marker-indexed SQL cache MCP server that indexes in-file @scry.\* markers into a SQLite database, enabling agents to query structured project knowledge via read-only SQL without LLM reasoning.

Provides MCP tools to read, write, append, and edit prose sections of nodes, backed by an in-memory or substrate-direct (Urania) backend.

Read-only MCP server that surfaces contradictions in an Obsidian vault's knowledge graph via semantic search and reasoning edges.

Hermetic memory for AI agents — one Rust binary, one SQLite file, zero network. Recall returns evidence with provenance or abstains: no code path for making things up.