selvage-lab/selvage C MCP Server Active
LLM-based code review MCP server with AST-powered smart context extraction. Supports Claude, GPT, Gemini, and 20+ models via OpenRouter.
Browse all Model Context Protocol servers with quality scores, stars, languages and maintenance activity.
LLM-based code review MCP server with AST-powered smart context extraction. Supports Claude, GPT, Gemini, and 20+ models via OpenRouter.
Semantic Scholar MCP server: 14 typed tools over 200M+ academic papers — search, paper/author retrieval, citation-graph traversal, and recommendations. `uvx s2-mcp-server`
MCP server for [YADE](https://yade-dem.org/) — open-source discrete element method (DEM) engine for granular and particle simulation. Browse API docs with BM25 search, execute code via synchronous REPL or async background tasks, monitor progress, and review task history.
Run AI agents in Zulip as @mentionable bots — or wire into any MCP client. Real-time listening, session management, file handling.
A Model Context Protocol server for managing, monitoring, and querying data in [CockroachDB](https://cockroachlabs.com).
Local-first semantic memory server with hybrid search, plain Markdown storage, MLX or CPU embeddings, contradiction detection, time-travel history, synthesis, and cross-machine git sync.
Persistent local memory for Claude Code. Indexes every session JSONL verbatim into SQLite + ChromaDB for semantic recall (~126ms) across your entire history. Never summarizes, zero API calls, 17 MCP tools including fuzzy `recall`, deterministic `replay_file`, and git-aware `recall_project_status`. Published on PyPI as `longhand` and registered in the MCP Registry.
Secure, local-first MCP server exposing ArcGIS Pro's ArcPy engine over stdio JSON-RPC, with worker-process isolation, PathGuard filesystem boundaries, and 100 geoprocessing tools.
Polarion ALM integration with 24 read/write tools for documents, work items, traceability links, and comments. Renders documents as Markdown, searches with Lucene or SQL, walks incoming/outgoing links, and creates/updates/reorganizes work items. Every write tool supports `dry_run` with pre-write field, enum, and link-target validation. Requires Polarion 2506+. `uvx mcp-server-polarion`.
Keyless remote MCP server for German public infrastructure open data: weather, air quality, traffic, public transit, parking and roadworks across 84+ German cities (DWD, Umweltbundesamt, Mobilithek, GovData). 38 read-only tools.
Read-only VMware vSphere/vCenter monitoring — inventory, alarms, events, host health, VM info, and snapshot listing. 8 strictly read-only tools with code-level zero-destructive guarantee (validated by test fixtures).
Hydrolix time-series datalake integration providing schema exploration and query capabilities to LLM-based workflows.
Coherence guard for shared files: when two agents write the same file, the stale writer is denied instead of silently overwriting, then reacquires and retries. Single-host, TLA+-verified. Install: `uvx --from "agent-coherence[mcp]" stale-write-guard-fs`.
Local-first Obsidian vault MCP server for Codex, Claude Desktop, and other MCP clients. Works directly with markdown files, no Obsidian plugin, API key, cloud service, or running Obsidian app required. Includes read-only mode, backup-on-write, path isolation, and setup examples.
An MCP server for accessing Vectara's trusted RAG-as-a-service platform.
Local-first CLI and MCP wrapper for AI coding agents. Routes shell commands through `sage run --`, stores command history locally, and returns compressed terminal output to reduce context noise.
Local, contract-governed federation across files and databases (Postgres, Snowflake, BigQuery, DuckDB, Excel, and more) with read-only guards, PII masking, and per-column agent access.
Design-time KNX/ETS6 assistant: parses .knxproj (read-only, no bus access), validates DPT/naming/command-status pairing, and generates Home Assistant YAML + ETS XML/CSV exports.
Persistent AI memory with SQLite hybrid search (FTS5 + semantic). Built-in Qwen3 embedding, rclone sync across machines. Zero config, no cloud, no limits.
Natural-language search and review of South Korea's national R&D (research & development) regulations (acts, decrees, and administrative rules), returning the current in-force provisions with citations, fetched live from the official national law database.
Website & web-app testing built for AI agents rather than raw browser bindings: 66 Playwright tools with hard assertions, auto form-fill, persistent authenticated sessions (incl. interactive login for 2FA/SSO), network mocking, real INP, and accessibility/SEO/GEO (llms.txt, AI-crawler access, WebMCP) + Lighthouse audits.
Read-only trust layer for Postgres: the agent never writes SQL — twelve tools compile it from definitions you control, PII and secret categories are refused before the query runs, and every call lands in a tamper-evident SHA-256 audit chain.
Airtight math for agents: 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.
On-demand Obsidian vault access via MCP. Adaptive context loading (67-82% token savings), full-text and ranked search, health checks, auto git commit, and worker delegation to cheaper models. 10 tools, works with any MCP client.
Zero-config data quality monitoring across Postgres, BigQuery, Snowflake, MySQL, and DuckDB. Profile a warehouse, detect anomalies (volume, schema drift, freshness, NULLs, distribution, cardinality), with optional dbt manifest lineage. Read-only — connection resolved server-side, never passed via the model.
Modern, cross-platform MCP server enabling AI assistants to browse and interact with both Gopher protocol and Gemini protocol resources safely and efficiently. Features dual protocol support, TLS security, and structured content extraction.
Service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents. Versioned Markdown store, pub-sub notifications, diff-aware updates, and lifecycle stage tracking. Each service registers as a sub-project; agents subscribe to cross-service document changes and receive structured diffs via MCP.
Macro-factor quantitative trading signals for AI agents. 8 tools for strategy discovery, live signal retrieval, and self-service trial registration. Covers US and A-Share markets with forward-tracked performance.
Self-hosted coordination layer for AI agent fleets. Shared semantic memory, tasks, agent-to-agent messages, session handoffs, and a background archivist that synthesizes cross-agent knowledge. Any HTTP client participates — Claude Code, AutoGen, raw scripts.
Git-first memory for AI agents: Markdown files are truth, the index is disposable, and writes are reviewable commits. Ships 7 MCP tools (hybrid search, read_note, build_context, resolve, think, list_folders, and a scope-gated commit_note write) over a Streamable HTTP endpoint, plus a CLI and a read-only Obsidian companion.
Read-only-by-default MCP server for [Datanika](https://datanika.io), the open-source ELT + dbt platform: browse connections, preview data, run and compile dbt transforms, monitor runs, and manage pipelines. 25 tools; opt-in `--allow-write` enables create/trigger.
Peil — financial orientation for Dutch freelancers (ZZP'ers): log hours, draft invoices from unbilled time, and ask where you stand — outstanding, overdue, and your net effective hourly rate. Scoped API keys with draft-by-default: putting email in front of a client needs a separate `invoices:send` permission the key can be issued without. `uvx peil-mcp`
Read, create, update and delete Google Keep notes.
Interact with [Twelve Data](https://twelvedata.com) APIs to access real-time and historical financial market data for your AI agents.
MCP server for RAGStack serverless knowledge bases. Search, chat with AI-generated answers, upload documents/media, scrape websites, and analyze metadata through an AWS-powered RAG pipeline (Lambda, Bedrock, S3, DynamoDB).
An MCP server for searching and downloading royalty-free stock photography from Pexels and Unsplash. Features multi-provider search, rich metadata, pagination support, and async performance for AI assistants to find and access high-quality images.
Discover and compare L402 + x402 paid API services from satring.com, the best curated Lightning and USDC API directory.
NanoBanana AI image generation and editing with virtual try-on and product placement in realistic scenes.
Local, read-only retrieval over official Python standard library docs with exact symbol lookup, section-level results, and version-aware context.
MCP server over your Claude Code transcript history — full-text + semantic search, byte-identical thread recall, durable /remember facts. Local SQLite, stdlib-only.
A meta-server for minimal Claude Code tool bloat with progressive disclosure and dynamic server provisioning. Exposes 9 stable meta-tools, auto-starts Playwright and Context7, and can dynamically provision 25+ MCP servers on-demand from a curated manifest.
MCP server implementation for PythonAnywhere cloud platform.
A Model Context Protocol (MCP) server designed to connect to a CCTV recording program (VMS) to retrieve recorded and live video streams. It also provides tools to control the VMS software, such as showing live or playback dialogs for specific channels at specified times.
AI enhancement middleware: precise retrieval replaces full-memory loading (~80%+ token cut), rule-based conflict arbitration with explainable reasons, and one local SQLite shared across Claude Code/Codex/Cursor/ZCode. Local-first, zero cloud, MIT. `pip install memory-arbiter-mcp`
Durable hybrid memory for AI agents. Combines vector search, BM25, temporal retrieval, and optional Memgraph knowledge graph via reciprocal rank fusion. 6 MCP tools: health, search, answer, feedback, graph_query, graph_add_triple. Self-hosted with Qdrant backend. 82.5% strict accuracy on LoCoMo benchmark. `pip install 'mnemostack[mcp]'`
Auditable strategic-risk memos for AI agents — sanctions, regulatory, geopolitics, trade. Geography-routed regional specialists (Central Asia/Caspian, Gulf/Middle East), per-claim evidence discipline, schema-validated output, machine-verified audit. No live data retrieval. PyPI: `agenda-intelligence-md`.
Personal travel agent with 66 tools — flights, hotels, visa checks, itinerary planning, travel advisories, currency conversion, passport power index, and credit card points/miles optimization. Offline-capable profile stores home airports, passports, and card portfolio. Install: `pip install wander-agent`.
Convert `.eml` email exports to clean Markdown with YAML front matter — thread splitting, signature stripping, attachment extraction, and calendar parsing. Tuned for feeding archived email into RAG/LLM pipelines.