"OSF" matching MCP servers:

Read-only MCP tools for authenticated Open Science Framework projects, components, files, and contributors.

Enables AI agents to submit npm, PyPI, Go, or Maven packages and manifests to the free OSV.dev database and receive per-package and per-advisory results with CVE mappings, CVSS scores, severities, and the versions that fix each issue. It also supports filtering by minimum severity, de-duplicating alias advisories, and machine-readable error/warning rows for CI gates and upgrade recommendations.

An MCP server that provides access to the Library of Babel, allowing users to retrieve exact page contents by address, search for text to find its location, and generate random pages.

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

MCP server for token-efficient access to Open Finance Brasil rules, enabling coding agents to search and retrieve specific regulations, OpenAPI specs, and business rules through progressive disclosure.

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.

Visual CVE audit dashboard for npm, Python, Go, and Rust projects. Scans your project manifests (package-lock.json, requirements.txt, go.sum, Cargo.lock) against OSV.dev live data, opens a browser dashboard for human review, then applies fixes only after explicit confirmation. Supports multi-service monorepos in one command.

Bilingual (EN/ES) AI-writing detection that shows the evidence instead of a percentage: named tells with line and column, hidden-character inspection, and citation cross-checking against a document's own bibliography. Seven of its nine tools run entirely locally and never touch the network.

Provides MCP tools to search, retrieve, and answer questions from the public Open Finance Brasil Confluence documentation using BM25-based local indexing.

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

MCP server providing tools to verify task completion (tests pass and changes match claim) and confirm bug reproduction before fixing.

Gives every AI agent you use one shared, versioned memory in a local SQLite file, so a fact saved from one app is found by all the others. Runs fully offline with no API key, records which agent wrote each change, and keeps every prior version so nothing is silently overwritten.

An MCP server that enables natural language querying and troubleshooting of Kubernetes clusters, supporting multi-cluster switching and providing tools for pods, nodes, events, and logs.

Enables AI agents to start, control, and verify local open.mp/SA-MP game servers via MCP stdio, using a headless RakClient to send allowed slash commands and assert round-trip responses.

Gives any MCP client the same sandboxed coding-agent toolset — searching, viewing and editing files, running tests, and executing shell commands — each session in its own locked-down, network-isolated Docker container. Enables an MCP-capable assistant to diagnose and fix failing tests without touching the host machine.

MCP server for searching and exporting Apple SF Symbols as true vector SVGs.

Enables agents to convert local files across 162 input formats and 3649 proven conversions, using two tools to list supported formats and convert files with clear error reporting.

Build AI trading agents on Eterna Hybrid Exchange (no-KYC perp DEX with flat 0.014%/0.035% fees). Works out of the box with fee estimation, venue comparison, setup guides and guarded agent prompts; add an Eterna token to bridge the official trading tools.

An MCP server that provides LLMs with full read/write access to an Open Knowledge Format (OKF) knowledge bundle, enabling structured, persistent long-term memory.

Enables multiple isolated Claude sessions to read markdown knowledge bases versioned in git and deposit proposals, while only a manager role integrates changes.

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.

Walkie-talkies for AI coding agents: Claude Code, Codex, Cursor and any MCP client message other developers' agents directly, peer to peer over HyperDHT and end-to-end encrypted. No server, no account. Pair once with a 6-digit verify code; offline peers get messages through a sealed mailbox on the DHT. Tools: send_message, read_inbox, list_messages, list_peers, get_status.

Provides transactional intelligence for AI agents, enabling safe tool execution with pre-flight invariant checks, sub-second filesystem snapshots/rollback, causal tracing, belief contradiction detection, and 15 native MCP tools for Claude Code.

Stops AI agents reopening rejected decisions and forgetting project state. Persistent operational state for agents: decisions, plans, blockers, priorities and patterns that survive across sessions, with enforcement. Not conversation logs.

Enables AI agents to shop and query Magento/Mage-OS stores via the storefront GraphQL API, including product search, stock checks, category browsing, cart management, and customer order status.

An MCP server that lets AI clients search and retrieve Doctor of Credit articles, categories, and deals via flexible tools, interpreting article content at request time.

Exposes a Notion-synced AI OS as read-only MCP tools, enabling MCP-compatible AI clients to search the vault, fetch page contents, list projects, and check project statuses without scraping public links.

An MCP server adapter that allows LLM agents to autonomously play World of ClaudeCraft by wrapping the game's headless environment as MCP tools for state reading and action execution.

Enables code agents to persist and recall durable project knowledge — rules, decisions, procedures, learnings and secrets — across sessions at low context cost, with accent-insensitive PT-BR search, scoped per repository/workspace, and secrets that stay out of the model's context.

Enables scanning Java (Maven) projects for known vulnerabilities via natural language, returning severity-sorted reports with CVSS scores and fix versions.