-
MCP client for APIbase.pro — connect AI agents to APIbase's live tool catalog (counts: https://apibase.pro/llms.txt). Dual-rail payments: x402 (USDC on Base) + MPP (USDC on Tempo/Stripe).
Version check not run yet
Finance and payments npm Local 48 a week MIT
@E
@egchq/egc io.github.fmarzochi/egc 2.1 · 43/100 EGC is a local-first MCP runtime that gives every AI agent the same brain: persistent shared memory, security guardrails, and up to 90% token savings across 20 AI coding tools.
Version check not run yet
Memory and context npm Local 48 a week APACHE-2.0
-
The explainable agent framework — backtrack a wrong answer to the exact context that caused it (evidence, not guesses). Built on footprintjs.
Not run: no command to start
Model and agent tools npm Local 2.2k a week MIT
-
101 tools for WooCommerce store management with field filtering and guided prompts.
Version check not run yet
E-commerce Official MCP Registry · npm Local 71 a week MIT
OR
Oroute io.github.netclaus/oroute 2.1 · 42/100 Auto-route AI requests to 13 models (Claude, GPT, Gemini, Qwen, DeepSeek). 57% cost savings.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 36 a week MIT
-
OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 21 a week MIT
GI
GEO Inspector io.github.Bigsupe55/geo-inspector-mcp 2.1 · 42/100 Inspect a site's AI-search readiness: AI crawler access, llms.txt, schema markup, meta directives
Version check not run yet
Maps and location Official MCP Registry · npm Local 21 a week MIT
SA
Sagemath io.github.justice8096/sagemath-mcp-server 2.1 · 42/100 MCP server wrapping SageMath's full computer algebra system — 10 symbolic-math tools for LLMs.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 21 a week CC0-1.0
-
Search, browse and pick from the free NerdyChefs.ai prompt library from any MCP client.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 21 a week MIT
MA
Manoma io.github.paperdavid/manoma 2.1 · 42/100 MCP server for soul.md — your portable AI identity layer across every LLM.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 21 a week MIT
JS
jsonshim org.toolkitlabs/jsonshim 2.1 · 42/100 Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 21 a week CC0-1.0
-
MCP Server for understanding, managing & troubleshooting your GCP environment.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local APACHE-2.0
MD
Mdma io.github.MobileReality/mdma 2.1 · 42/100 MCP server for MDMA — exposes spec, prompts, docs, and package metadata to AI assistants.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 59 a week
CL
Clawbackai io.github.Rckl88/clawbackai-mcp 2.1 · 42/100 LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.
Version check not run yet
Model and agent tools Official MCP Registry · npm Local 31 a week MIT
MC
McpOrchestrator io.github.Byggarepop/dotnet-mcp-orchestrator 2.1 · 42/100 Route one agent through one MCP server to many, with progressive tool discovery to shrink context.
Version check not run yet
Model and agent tools Official MCP Registry · NuGet Local MIT
-
Search agent skills ranked by measured lift vs a no-skill baseline, with safety and rankings.
Version check not run yet
Model and agent tools Official MCP Registry · PyPI Local MIT
AI
ai·rete·rag com.ai-rete-rag/ai-rete-rag-mcp 2.1 · 42/100 Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
100% up · 30 days
Search and retrieval (RAG) Official MCP Registry · PyPI Local Remote MIT
-
Human approval for AI agents: a named person approves or rejects, silence is not consent.
Version check not run yet
Model and agent tools Official MCP Registry · PyPI Local MIT
-
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
Version check not run yet
Model and agent tools Official MCP Registry · PyPI Local MIT
-
Consistency verdicts for MCP tool calls: no two agents consume the same resource version twice.
Version check not run yet
Model and agent tools Official MCP Registry · PyPI Local APACHE-2.0