{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_k2e6f258xpdk","handle":"mcp-rlm-proxy","url":"https://wellknown.network/agents/mcp-rlm-proxy","links":{"self":"https://wellknown.network/agents/mcp-rlm-proxy/record.json","html":"https://wellknown.network/agents/mcp-rlm-proxy","markdown":"https://wellknown.network/agents/mcp-rlm-proxy/record.md","api":"https://wellknown.network/api/v1/agents/mcp-rlm-proxy","status":"https://wellknown.network/api/v1/agents/mcp-rlm-proxy/status","claim":"https://wellknown.network/agents/mcp-rlm-proxy/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-rlm-proxy/claim.json","badge":"https://wellknown.network/agents/mcp-rlm-proxy/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-rlm-proxy/history","tools":"https://wellknown.network/api/v1/agents/mcp-rlm-proxy/tools"},"ard":{"identifier":"urn:air::server:mcp-rlm-proxy","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-rlm-proxy","summary":"MCP-RLM-Proxy: Intelligent MCP middleware with RLM-style recursive exploration, smart caching, and proxy tools.","description":"# MCP-RLM-Proxy: Intelligent Middleware for MCP Servers\n\n> **Production-ready middleware** implementing Recursive Language Model principles ([arXiv:2512.24601](https://arxiv.org/abs/2512.24601)) for efficient multi-server management, automatic large-response handling, and first-class proxy tools for recursive data exploration. **100% compatible with the MCP specification** - works with any existing MCP server without modification.\n\n## Quick Start for Current MCP Users\n\n**Already using MCP servers?** Add this as middleware in 5 minutes:\n\n```bash\n# 1. Install\npip install mcp-rlm-proxy\n\n# 2. Create a config in your working directory (mcp.json)\nmcp-rlm-proxy --init-config ./mcp.json\n\n# 3. Edit mcp.json to add your servers\n$EDITOR ./mcp.json\n\n# 2. Configure your existing servers\ncat > mcp.json << EOF\n{\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol/server-filesystem\", \"/your/path\"]\n    }\n  }\n}\nEOF\n\n# 3. Run the proxy\nmcp-rlm-proxy --config ./mcp.json\n```\n\n**That's it!** Your servers now have automatic large-response handling and three powerful proxy tools for recursive exploration.\n\n---\n\n## Why Use This as Middleware?\n\n### The Problem with Direct MCP Connections\n\nWhen AI agents connect directly to MCP servers:\n- **Token waste**: 85-95% of returned data is often unnecessary\n- **Context pollution**: Irrelevant data dilutes important information\n- **No multi-server aggregation**: Must connect to each server separately\n- **Performance degradation**: Large responses slow everything down\n- **Cost explosion**: Every unnecessary token costs money\n\n### The Solution: Intelligent Middleware\n\n```\n+---------------+\n|  MCP Client   |  (Claude Desktop, Cursor, Custom Client)\n+-------+-------+\n        | ONE connection\n        v\n+---------------+\n| MCP-RLM       |  <-- THIS MIDDLEWARE\n| Proxy         |  - Connects to N servers\n|               |  - Auto-truncates large responses\n|               |  - Caches + provides proxy_filter…","publisher":{"name":"MCP-RLM-Proxy Contributors","url":null},"homepage":"https://github.com/pratikjadhav2726/mcp-rlm-proxy#readme","repository":"https://github.com/pratikjadhav2726/mcp-rlm-proxy#readme","version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["ai","llm","mcp","model-context-protocol","proxy"],"pricing":null,"endpoints":[{"url":"pypi:mcp-rlm-proxy","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.filesystem","name":"Filesystem","confidence":1,"provenance":"derived"}],"categories":["dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-rlm-proxy","registry":"pypi","observedAt":"2026-11-03T15:23:06.737Z","publishedAt":"2026-02-18T10:10:20.275034Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-rlm-proxy","url":"https://pypi.org/project/mcp-rlm-proxy/","firstSeenAt":"2026-09-10T03:19:21.444Z","fetchedAt":"2026-11-03T15:21:16.373Z","normalizedAt":"2026-11-03T15:21:16.373Z"}]},"firstSeenAt":"2026-09-10T03:19:21.444Z","updatedAt":"2026-11-03T15:23:06.737Z"}