"OSF" matching MCP servers:

Memory vaults on your own machine, one per life domain, retrieved with a local BM25 index fused with vector search, where the human decides which vaults a model may answer from. Requires the Mnemosyne OS desktop app running locally; it also reports what other coding agents on the same machine are doing.

Local-first memory engine for AI-agent teams: private/team/project ACL, associative recall, and federated sync across nodes. One SQLite file, no LLM required.

Provides a persistent, branching store for fictional scenes — stories, character assignments, turns and editable summaries — exposed as ten validated, revision-checked MCP tools. Supports optimistic concurrency, idempotent turn appends, canon rules and story export over a bearer-token-authorized HTTP boundary that fails closed.

Enables source-first orchestration and knowledge indexing with inspectable architectural capabilities through a unified MCP interface, including named-attribute retrieval and atomic knowledge ingestion.

Enables Codex projects to read Git-backed kickoff, acceptance, handoff, progress, and next-step context, and to append validated, audited progress events through scoped MCP tools. This supports visible agent progress, resumable sessions, and safer handoffs.

An LLM-native decision tracking system that captures unexpected engineering outcomes as 'pressure events' to build a persistent learning foundation. It enables AI assistants to manage cases, log surprises, and promote recurring insights into global or project-specific knowledge bases.

Enables sophisticated reasoning workflows using graph-based representations for AI models.

Enables AI agents to retrieve Git-backed project context, handoff packages, progress, and next steps, and to append validated progress events with matching project-record commits. This supports visible agent progress, resumable work, and safe handoffs while keeping high-risk actions outside the MCP surface.

MCP server that integrates OpenAI Codex with Open Knowledge Format (OKF), enabling knowledge bundle validation, capture, diffing, and workflow automation through natural language.

Enables agents to read Git-backed project context and append audited, idempotent progress events through scoped, short-lived credentials, supporting resumable handoffs and visible project state.

Enables AI agents to read Git-backed project context and append validated, audited, idempotent progress events through short-lived, scoped credentials, supporting resumable work and safer handoffs.

Turn any website into a book you agent can read

MCP server that provides AI agents with persistent memory, cross-agent sharing, and context management, enabling them to remember conversations, track complex tasks, and evolve skills across tools.

Serves an AI coding agent a searchable index of a codebase's existing capabilities and past incidents, so it can find and reuse what already exists before writing new code. Also exposes blast-radius analysis for shared code and lets the agent reindex the knowledge base, all via local retrieval with no model calls or API keys.

Bridges MCP to a self-hosted Mem0 OSS server, enabling memory management operations like adding, searching, updating, and deleting memories.

MCP server for managing an OKF markdown knowledge base, enabling AI agents to query, read, write, and auto-sync architectural decisions and rules via Git.

A scientific reasoning framework that leverages graph structures and the Model Context Protocol (MCP) to process complex scientific queries through an Advanced Scientific Reasoning Graph-of-Thoughts (ASR-GoT) approach.

Reusable, read-only MCP server that exposes a repo's knowledge files (backlog docs, decisions, design notes) as MCP resources over stdio.

Serves folders of an Obsidian vault to AI agents over MCP as Open Knowledge Format bundles, letting them browse, search, read, graph and write draft notes with recorded provenance and checkable trust. Agents can propose changes, but only the user approves them, and stale or externally edited content is flagged rather than trusted.

Enables browsing, searching, and expanding a knowledge base of markdown nodes with YAML frontmatter from within a chat, supporting document ingest and generative HTML widgets.

Enables Codex agents to read a project's kickoff card, acceptance criteria, progress, Git trail, and handoff package, then append one validated, idempotent progress event with an agent verification note and matching Git commit. Access is limited to short-lived, scoped, revocable credentials bound to a single workspace and project, with high-risk actions kept outside the tool surface.

Enables MCP clients to read a project’s kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, and to append validated, audited, idempotent progress events as Git-backed project records.

Enables Codex and MCP clients to read a project's kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, and to append validated, audited, idempotent progress events tied to project-record Git commits.

Enables agents to retrieve project context and append validated, audited progress events through scoped MCP tools, keeping project records Git-backed and handoffs resumable.

Enables AI agents to retrieve Git-backed project context—kickoff cards, acceptance criteria, handoffs, progress, and next actions—and to append validated, audited progress events under scoped credentials.

Enables Codex agents to pull a project's kickoff card, acceptance criteria, AGENTS rules, handoff package, progress, Git trail, and next step, then append a single validated, audited, idempotent progress event with a matching project-record commit. Access is scoped to one short-lived, revocable credential bound to a single workspace and project.

Enables semantic search over local knowledge bases like Obsidian notes, SQLite, and plaintext files, exposing results to Claude via MCP server.

Enables safe local system command execution, file operations, hardware diagnostics, and persistent cross-session memory storage via SQLite.

Enables agents to interact with OKF bundles: browse, search, read concepts, and audit trust and freshness.

An MCP server for managing contextual data as markdown files with metadata, enabling agents to save, retrieve, search, and delete contexts using simple CRUD operations.