MCP server directory

Disney Lorcana TCG card search, deck analysis, ink curves, lore generation, and franchise browsing. 7 tools, 2,710 cards embedded.

Historical stock chart pattern intelligence for AI agents. 24M pre-computed embeddings across 15K stocks and 10 years of data. Search by ticker+date or screenshot to find the most similar historical patterns and see what happened next. 19 tools including pattern search, forward returns, regime analysis, and trade simulation. Install: `pip install chartlibrary-mcp`. Free tier: 200 calls/day.

Decision intelligence MCP server with 19 algorithms (bandits, Monte Carlo, constraint optimization, forecasting, anomaly detection, risk analysis, graph algorithms), 28 MCP tools. Install via `npx -y @oraclaw/mcp-server`.

An MCP (Model Context Protocol) server that provides tools for querying OCI registries and image references. This project implements an SSE-based MCP server that allows LLM-powered applications to interact with OCI registries. It provides tools for retrieving information about container images, listing tags, and more. - Get information about OCI images - List tags for repositories - Get image manifests - Get image configs The server provides the following MCP tools: - image_ref: The image reference (e.g., docker.io/library/alpine:latest)

4 tools · get_image_config, get_image_info

Argentine exchange rates for AI agents via DolarAPI. Dollar blue, oficial, MEP, CCL, crypto, tarjeta — plus currency conversion and spread calculator.

49-tool Polymarket prediction market suite for AI agents. Direct trading, smart money flow detection, copy trading with auto-monitor, backtesting, arbitrage scanning, portfolio optimization, and real-time WebSocket price streaming. Preview mode for simulation, live mode for real orders.

Read-only, offline analysis of your own stock/ETF transaction log — drawdown-first risk with bootstrap confidence intervals and walk-forward verdicts, computed by a validated deterministic core and served to the model as read-only tools it reports rather than recomputes; publishes a `portfolio://guarantees` trust manifest.

Free company research agent — 10 data sources, structured reports with bull/bear verdict in ~10 seconds. Stocks, crypto, and private companies.

Access comprehensive, real-time financial data (stocks, options, crypto, forex) via developer-friendly, AI-native APIs offering unbeatable value.

> Connect Claude, Cursor, and other AI coding tools to the Zerion API docs through the Model Context Protocol server for in-editor answers and code generation. The Zerion API docs are available as a Model Context Protocol (MCP) server. Once connected, your AI tool can search our full documentation and OpenAPI spec while generating code - no copy-pasting needed. Once connected, you can ask your AI assistant things like: "How do I get a wallet's token positions on Ethereum?" "Write a Python script that fetches transaction history and filters for trades" "What filters are available on the positions endpoint?"

3 tools · Explore endpoint capabilities, Generate integration code

Solana token risk scoring and pump.fun graduation signals. Score any token by mint address (0-100 risk, risk_label, holder concentration, liquidity), detect graduation momentum (buy/sell ratio, velocity), and query trust attestations. Live API. Freemium — 4 free tools, PRO via x402 micropayments ($0.01/call USDC).

Crypto rates (lending, staking, borrowing), coin metadata, aggregated prices, market stats, stablecoin peg-stability, and symbol resolution. 18 tools. Hosted at `api.bitcompare.net/mcp` or via `npx @bitcompare/mcp-server`.

🎖️ 📇 ☁️ - MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data.

MCP server that compiles AI browser automation into deterministic `.tap.json` plans (25-op closed union, zero runtime LLM), runs on your logged-in Chrome, and detects drift via semantic fingerprint diff when sites change. 65+ open community taps on 40+ sites.

Bitte Protocol integration to run AI Agents on several blockchains.

Philippine government data as agent-callable tools: PHIVOLCS earthquakes + volcano alerts, PAGASA weather + typhoons, PhilGEPS procurement, PSA 2020 Census population + poverty, AQICN air quality. Install: `uvx ph-civic-data-mcp`.

Search and fetch research datasets across Zenodo, DataCite (Dryad/Figshare/Dataverse/OSF), NCBI omics (GEO/SRA/BioProject), and literature (PubMed/OpenAIRE) behind one normalized model — DOI deduplication, NCBI-Taxonomy synonym expansion, paper→data linking, and checksum-verified download. `uvx data-aggregator-mcp`.

Physics-based anomaly detection via MCP. Uses Klein-Gordon wave equations on GPU to detect anomalies with high precision (avg 0.90). 9 tools: scan, fingerprint, compare, token risk, wallet profiling, volume check, price manipulation detection.

The MCP server has been moved into the PostHog Monorepo - you can find it here. Documentation: https://posthog.com/docs/model-context-protocol You can install the MCP server automatically into Cursor, Claude, Claude Code, VS Code and Zed by running the following command:

Semantic Scholar MCP server: 14 typed tools over 200M+ academic papers — search, paper/author retrieval, citation-graph traversal, and recommendations. `uvx s2-mcp-server`

Durable, local-first memory for AI coding agents over MCP. Zero-dependency (pure Python + SQLite/FTS5), curated and semantically de-duped — you own the data as plain rows. Works with Claude Code, Codex & any MCP host. `uvx --from yggdrasil-memory ygg mcp`

MCP server for the Dingo: a comprehensive data quality evaluation tool. Server Enables interaction with Dingo's rule-based and LLM-based evaluation capabilities and rules&prompts listing.

Personal knowledge graph shared across MCP clients. Account-keyed and portable as a `.polarity` file, with sources for iMessage, browser history, calendar, Claude Desktop transcripts, shell history, Notion, and Obsidian. `npx -y @polarity-lab/cosmos-mcp`

Local-first memory for long-horizon AI agents with no LLM at ingest — $0 per message, zero data egress, verbatim source-traceable recall. Typed belief revision, selective forgetting, and a provenance guard that blocks memory-justified destructive actions unless user-confirmed. One `midas init` wires Claude Code, Cursor, Codex, and 6 more clients to one shared SQLite memory; local web inspector and hash-chained audit log. Benchmarked on LongMemEval/LoCoMo/BEAM with one-command repros — including published negatives. `uvx midas-memory-mcp` or `npx -y midas-memory-mcp`

Developer context continuity system. Watches your git repos and builds a temporal knowledge graph of modules, symbols, decisions, and open problems via Graphiti + Neo4j, then serves it to any AI coding agent over MCP. Every edge carries a validity window and a confidence score that decays over time. 12 tools across read and write. Install via `npx -y stifler-memex-mcp`. MIT licensed.

Self-hostable, markdown-native team wiki with a built-in MCP server: agents search, read, and write your wiki pages (ranked Postgres full-text + semantic search, backlink traversal). Plus Atlas, which auto-generates a cited, coverage-checked wiki from your git repos and Jira. Go + Postgres. `npx tela-mcp`

Custody-free, policy-gated, receipt-backed execution layer for AI agents. 16 MCP tools across 18 chains (Base, Ethereum, Bitcoin native, Starknet, NEAR, Solana, Stacks, BNB, Rootstock, Filecoin, Aptos, Sui, TON, Tron, XRPL, Stellar, Algorand). One NEAR MPC key authority signs on EVM and BTC, no private keys held anywhere. ShadeGuard policy enforcement, Intel TDX TEE attestation, HMAC-SHA256 receipts, Filecoin and BTFS anchored. x402 protocol settlement with 0.25 percent protocol fee. Public discovery with no signup needed: call yax_get_capabilities without auth. Instant test key (5 USD cap, 7 day) via POST /api/apply. Install via `npx agentx402-mcp-server`.

Persistent memory for AI agents — store what matters, recall by meaning, skip the rest

Regulated-industry AI compliance knowledge as MCP. 6 tools (lookup_control · classify_use_case · crosswalk · walk_playbook · get_anti_pattern · list_regulations), 53 resources, 5 prompts. Covers EU AI Act, APRA CPS 230/234, NIST AI RMF, ISO 42001, AU AI Safety Standard (DISR Aug 2024), OWASP LLM Top 10, SLSA, SSDF, OAIC APPs, GDPR, DORA + 17 more frameworks. 56 controls × 28 regulations × 261 tools, 15 named anti-patterns, 20-entry crosswalk matrix. Apache 2.0 + CC BY 4.0 dataset. Install: `npx -y @hellouchit/mcp-regulated-ai-compliance`

MCP server providing accurate information about NixOS packages, system options, Home Manager configurations, and nix-darwin macOS settings to prevent AI hallucinations.

Generate, edit, and upscale AI video & images (Seedance, Veo, Kling, FLUX, Nano Banana) from any agent via VicSee.

Connect Claude, ChatGPT, Perplexity, Manus AI, and other AI assistants to FeedMansion. Draft posts and manage channels from your AI chat. Nothing publishes without your approval. > GitHub Repo: For platform-specific setup guides and example prompts, see github.com/makerprism/feedmansion-ai-agents The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools. FeedMansion runs an MCP server so your AI assistant can draft social media content in your brand voice and organize approved drafts into channels, all from within your AI chat. Nothing publishes without your explicit approval in FeedMansion.

5 tools · create_draft, get_scheduled_and_queued_posts

3D product viewer platform with a visual editor. Upload GLB models, style scenes with lighting, camera, and backgrounds, and embed on any website. `npx @vitrine3d/mcp`

Provides MCP multi-cluster Kubernetes management and operations, featuring a management interface, logging, and nearly 50 built-in tools covering common DevOps and development scenarios. Supports both standard and CRD resources.