"Ruby on Rails" matching MCP servers:

Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).

Live verifiable on-chain data for the $BOBAI token on BNB Chain: price computed from pair reserves × Chainlink (no price API), liquidity depth with LP-burn proof, buyback-and-burn audit trail, and fee-on-transfer-safe trade params. 13 read-only tools + 2 guided prompts, no API key.

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.

A neutral, non-custodial payment router for AI agents: it discovers which payment rails a paid endpoint accepts (x402 on Base/EVM, Solana, MPP), then pays across them using the caller's own wallet key. Three tools — discover_payment_rails, pay_for_resource, payment_history.

Drive open-source Gearotons M17 servomotors from natural language via an MCP server with safety rails and a mock backend.

Lets Claude and other MCP hosts do real ABAP development on SAP systems through ADT: search objects, read and write source, transports, activation, ABAP Unit, ATC, short dumps, debugger and SQL queries. 173 tools, multi-system (S/4HANA Cloud and on-prem), with server-side guard rails and an audit log.

Laya-MLX as an MCP server (and plain-HTTP API). It answers typed decisions — choose an option / score a rubric / is this true? — on your own machine (Apple Silicon / MLX), with no cloud and ~10ms after warm-up. Not a chatbot. No token-by-token text, no JSON that can break. One forward pass returns a structured answer you can branch on. Ideal for routing, triage, classification, lead scoring, and g

A template for deploying MCP servers on Cloudflare Workers with OAuth authentication, enabling remote access to MCP tools via SSE transport from Claude Desktop and other MCP clients.

Live USPS, UPS, FedEx and DHL Express parcel rates from a US origin, domestic or to Canada, the UK, Germany and Australia, from a plain-words item description: no scale, no account, no API key. Also creates checkout links, reports checkout status, tracks parcels bought on smklog.com and serves a monthly US parcel price index.

Rug pull risk scores and on-chain forensics for memecoins on Solana, Ethereum, Base and Robinhood Chain - launch-bundle detection, funding-origin tracing, deployer history, insider networks and whale flow. 15 read-only tools.

MCP server for AI-assisted development on the Lampa open-source TV app, providing read-only access to the source tree with 41 tools and 5 resources for structured analysis, planning, editing, and validation.

Classifies job titles into department and seniority using deterministic rules, and optionally verifies if a person is listed on their employer's website via the Mamba Labs Contact Classifier Apify actor.

Source-backed hardware end-of-life (EOL/EOSL) lookups by part number for enterprise gear — support status, end-of-sale and end-of-support dates, with the vendor's own bulletin URL on every answer. Unknown parts return found:false, never a guess.

Bridges Microsoft Clarity's analytics API with Claude, enabling custom date ranges and page-level filtering on top of Clarity's native limitations.

Enables AI apps to work with Google Drive in plain language, including searching, organizing, uploading, downloading, exporting, sharing, and commenting on files, with reversible trash and configurable access scopes.

Local-first memory for coding agents. Discovers the memory, instructions, and rules Claude Code, Codex, and Cursor already wrote on your machine, combines them into one canonical Markdown tree, and serves grounded, cited recall through tools like ask_memory and canonical_memory.

Upload, list, and delete files on YourImageShare (free image & video hosting, 200MB limit, no account required) from Claude, ChatGPT, or any MCP-compatible agent.

Enables AI coding agents to retrieve relevant execution context before a task, compare candidate paths, log outcomes, and search past experiences stored locally in SQLite. It lets agents reuse what worked on similar tasks and get live alerts when a run stagnates or repeats failures.

Read-only on-chain query surface for the AgentCivics civil registry on Sui — soulbound AI-agent identities, on-chain memories, reputation, refusal records. Hosted, no install, no keypair. For write tools (register, write_memory, record_refusal), install the npm package @agentcivics/mcp-server locally and supply your own keypair.

Enables AI agents to call paid APIs and settle HTTP 402 payment challenges with USDC on Base, without private keys ever being involved.