Task · Customer Support
Best AI agents to answer customer questions
This task needs 2 capabilities. 5 tools cover all of them; 517 cover at least one.
| # | Tool | Coverage | Access | Trust | Seen |
|---|---|---|---|---|---|
| 351 | sf-intelligence — Salesforce org intelligence for AI agentsMCP Offline, read-only MCP knowledge base for one Salesforce org's metadata, deps & impact. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 352 | PeopleMCPMCP Semantic search for people, projects and AI agents by task, skills and collaboration needs. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 353 | dockase-legal-mcpMCP Nigerian & Commonwealth legal reasoning, RAG search, contract analysis, and citation verification. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 354 | Obsidian Vault MCP ServerMCP Access Obsidian vaults via Local REST API - read, search, and interact with notes | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 355 | claude-memory-managerMCP Cross-session memory for Claude Code — context capture, semantic search, recall | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 356 | TriliumNext (trilium-mcp)MCP Read and write a self-hosted TriliumNext knowledge base over its ETAPI. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 357 | contextual-mcp-serverMCP RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 358 | dubstrataMCP Dubstrata: Causal Financial & Narrative CDN providing Graph RAG & Deep Research Reports | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 359 | vector-memoryMCP Semantic document memory using Redis vector store. Save and recall files with natural language. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 360 | citecite-mcpMCP Inject, parse, and strip [N] citation markers in RAG outputs. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 361 | ragdrift-mcpMCP Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 362 | intercomMCP Relays messages between two Claude Code sessions on different machines using the Channels API | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 363 | ragmetric-mcpMCP RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 364 | MidOS - MCP Community LibraryMCP Curated knowledge for AI agents — 19K chunks, 121 skills, semantic search via MCP | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 365 | Pipe (SPR) MCP ServerMCP AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 366 | ComfyUI BuilderMCP ComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 367 | Copilot Memory MCPMCP Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 368 | AgentLoreMCP AI-verified knowledge base with trust scoring, temporal facts, and skill cards. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 369 | freshvaultMCP Local semantic search over your Obsidian vault - always fresh, never reindex. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 370 | loomMCP Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 371 | pylon-mcpMCP MCP server for Pylon customer support platform | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 372 | IA-QA — 130+ QA & Dev Tools for AI AgentsMCP 130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 373 | lociMCP Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 374 | second-brain-bridgeMCP Search and reason over your Obsidian-style Markdown vault, right from ChatGPT. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 375 | mcp-file-processorMCP Text extraction, keyword extraction, language detection, and chunking for RAG | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 376 | agentsearch-mcpMCP LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 377 | memographMCP Graph-based memory system for LLMs with knowledge graphs and semantic search. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 378 | AgentNXMCP AI agents for federal IT & pharma: alert triage, ICAM, helpdesk, incidents, ticket routing. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 379 | IMAGIN.studio API DocsMCP Semantic search over IMAGIN.studio API documentation — CDN, API, integration guides, and more. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 380 | strajkpolski-mcpMCP Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, judiciary search, RAG. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 381 | google-surf-mcpMCP Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 382 | RAGScoreMCP Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 383 | woody-mcpMCP Woody, the AI firearms expert. Verified specs, legal lookups, and knowledge base. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 384 | marocain.investments — {GIN} real-estate intelligence (Morocco)MCP {GIN} verdict, M-Value AVM, market facts + semantic search for Moroccan real estate. Moat-safe. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 385 | velociragMCP Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 386 | ragstackMCP Search, chat, upload, and scrape a serverless RAGStack knowledge base on AWS. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 387 | gctrlMCP Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 388 | Repo-to-RAGMCP GitHub repository vectorizer and context synthesizer for RAG pipelines. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 389 | OmniClip RAGMCP Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 390 | Paper Distill MCPMCP Academic paper search across 11 sources with AI curation, ranked push, Zotero and Obsidian support. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 391 | stellavaultMCP Local-first MCP server: Claude searches, asks & drafts from your Obsidian vault. 21 tools, no keys. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 392 | Html Vers MarkdownMCP HTML to clean Markdown for LLM and RAG pipelines: headings, lists, tables, links, code fences. Pr... | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 393 | hubmeshMCP Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 394 | AiPayGen — 65+ AI Tools as an MCP ServerMCP 65+ AI tools as MCP: research, write, code, scrape, translate, RAG, agent memory, workflows | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 395 | cortexMCP Local repo context for coding assistants with semantic search and graph relationships. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 396 | ShelfmarkMCP Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 397 | Obsidian Semantic SearchMCP Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 398 | contextualMCP Persistent memory for AI coding agents: local-first semantic search, dependency graphs, git history. | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 399 | ariel-memoryMCP Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth | 50% | REMOTELOCAL | DECLARED | 5d ago |
| 400 | github-twinMCP Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP. | 50% | REMOTELOCAL | DECLARED | 5d ago |
Coverage = share of this task's required capabilities that an agent or tool documents. For AI agents, capabilities are those stated on the vendor's website; for tools, they are matched automatically from the publisher's description (keyword method, low confidence).