MCP Servers

MCP server for SPARKIT, a scientific research agent that searches the literature, reads papers, and returns cited Markdown reports. Submit a question via the research tool from Claude Desktop / Cursor / Claude Code; get back a ~90-second cited report without leaving the chat. uv tool

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:

Resolve any scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS bibcode, WHO IRIS URL) into structured CSL JSON, format in 10,000+ citation styles, or export to BibTeX/RIS/EndNote/Zotero RDF/CSV. Single or batch. Install: npx -y scholar-sidekick-mcp.

AI-native commercial disruption intelligence for MCP clients and x402-powered agents. Supports WARN/layoff intelligence, company context, geospatial territory disruption, and x402 payment challenge inspection via the hosted Forgemesh API.

All-in-one multimodal MCP for 300+ OpenRouter models: text chat, image / audio / video analysis, and image / audio / video generation (Veo 3.1, Sora 2 Pro, Seedance, Wan). Structured meta.code error taxonomy, IPv4+IPv6 SSRF guards, path-sandbox for disk writes, retry-after-aware backo

An MCP server to search for (free) stock images and videos from pexels.com.

Real-time cost observability for MCP tool calls. Transparent proxy auto-detects every MCP client (Claude Desktop, Cursor, Windsurf, VS Code, Claude Code, Zed, Continue.dev, Cline, Goose) and attributes spend per tool, per project, per end-customer. npx @mcpspend/proxy add install. Free tier 25K calls/month, no card. MIT pro

TypeScript MCP server for the Langfuse Public API. 27 read tools covering traces, observations, sessions, scores, score-configs, prompts (with version/label), datasets, dataset items, dataset runs, metrics, models, projects, comments, media, and health. Distributed as npx -y langfuse-mcp with provenance-signed releases.

Apple Ads (formerly Apple Search Ads) Campaign Management API v5 with 1:1 endpoint coverage — 74 typed tools across campaigns, ad groups, ads, creatives, custom product pages, targeting + negative keywords, performance reports, async impression-share reports, budget orders, ACLs, app/geo discove

Local-first dashboard + MCP server for Claude Code and Codex token usage. Cost, per-MCP/per-tool breakdown, hourly distribution, and session drill-down — your data never leaves your machine.

Audit how AI sees your website. Per-bot robots.txt verdicts for 22 known AI user-agents (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bytespider, etc), Cloudflare AI-default flags, on-page schema, sitemap, llms.txt, SPA-shell detection, and cross-model brand mentions via Perplexity + OpenRoute

42 local SEO tools for AI assistants. SERP tracking, Google Business Profile data, review monitoring, keyword research, citation audits, geogrid rank scans, AI visibility scoring, and competitive analysis. Install: npx @localseodata/mcp-server or connect to the hosted endpoint at mcp.localseodata.com.

French territorial intelligence MCP — cross-references public registries (FINESS healthcare facilities, RPPS health professionals, INSEE companies, IGN geocoding) for multi-source agentic reasoning over French open data.

Geographic data and live exchange rates: 250+ countries, 5K+ states, 150K+ cities, IP geolocation, and 161 currency rates in one MCP server. Requires APOGEOAPIKEY.

Persistent memory for AI agents with Ebbinghaus forgetting-curve decay, hybrid BM25+vector retrieval, and entity graph for multi-hop reasoning. Memories auto-prune by importance and recall rate. Built-in browser dashboard, multi-agent support, and yourmemory ask for zero-API-call local queries. pip install yourmemory

Session continuity engine that solves session orientation. Boot reports with gap detection and 100-point scoring, structured end-session capture with typed continuity records, and BM25 memory search. 7 tools, local SQLite + FTS5, zero API keys. npx rekindle

Persistent user identity across AI tools. Stores preferences, lessons, and decisions as local JSON; 13 core MCP tools share them with Claude Code, Cursor, Codex, and any MCP client. Knowledge governance (staging→verified), AES-256-GCM encryption, cross-tool sync. pip install piia-engram

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.

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, graphquery, graphaddtriple. Self-hosted with Qdrant backend. 82.5% strict accuracy on LoCoMo benchmark. pip install 'mne

Persistent memory + FTS5 full-text search for Claude Code conversation history. Indexes ~/.claude/projects/ JSONL into SQLite, exposes 10 MCP tools (store/recall/search memories, list sessions, get summaries) plus prompts. Includes a web UI for visual exploration with themes and exports. Works with Claude Code, Cursor, Codex, Windsurf, and any MCP-compatible client. npm install -g @kunwarshah/claudex

Compresses AI chat sessions into a typed knowledge graph (~300–800 tokens). Works file-based in Copilot, Claude Code, Cursor, and Gemini CLI without MCP server mode. Supports local/offline extraction via Ollama — no API key required.

Self-improving learning engine for Claude Code. Extracts signals from every session (corrections, successes, confusion), runs periodic reflections, and evolves behavioral frameworks through evidence tiers (hypothesis → observed → validated). Frameworks that keep working get promoted, bad ones get retired. 9 MCP tools, automatic hooks, phase-adaptive learning. Single dependency, local-only. npx claude-soul init --starter

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.

AI-powered paper annotation MCP server. Reads papers, highlights key findings with semantic color coding, explains formulas, and writes structured reading notes — all saved back to Zotero. Features two-phase workflow for large PDFs (63–80% context savings) and batch annotations.