Google PageRank for AI agents. 25,000+ tools indexed.

Best MCP Servers for LLM Client in 2026

455 tools indexed · avg score 89.4 · sorted by AgentRank score

The AgentRank index tracks 455 llm client tools. The top-ranked entry is agentic-community/mcp-gateway-registry at 94.6 points. Across the 10 shown here, the average AgentRank score is 89.4, and 10 had a commit in the last 30 days. The most common primary language is Rust.

LLM clients, gateways, and routers provide a unified interface for interacting with multiple AI model providers. These tools let developers and agents switch between OpenAI, Anthropic, Mistral, Google, and open-source models through a single API — enabling cost optimization, fallback routing, load balancing, and model comparison.

The category includes both SDK-level clients (thin wrappers around provider APIs) and full gateway deployments (proxy servers that add rate limiting, caching, cost tracking, and observability on top of raw model calls). LiteLLM is the dominant open-source option, with commercial alternatives like Portkey and Helicone for teams needing managed infrastructure.

Key features to evaluate: OpenAI-compatible API surface (so existing code works with zero changes), streaming support, token usage tracking, retry logic, and semantic caching. For production deployments, look for tools with Redis caching support to reduce costs on repeated queries.

Top 10 LLM Client MCP Servers

  1. #1
    agentic-community/mcp-gateway-registry

    Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI codin...

    94.6
    Ranks here on 942 GitHub stars and a commit within the last week, plus 83% of issues closed.
    Freshness
    30.8
    Issue health
    25.5
    Stars
    15.3
    Contributors
    12.3
    Description
    6.2
    ★ 942 commit today Python
  2. #2
    inference-gateway/inference-gateway

    An open-source, cloud-native, high-performance gateway unifying multiple LLM providers, from local solutions like Ollama to major cloud providers such as OpenAI, Groq, Cohere, Anthropic, Cloudflare...

    92.0
    Ranks here on 210 GitHub stars and a commit within the last week, plus 96% of issues closed.
    Freshness
    30.8
    Issue health
    29.7
    Stars
    11.9
    Contributors
    8.9
    Description
    6.2
    ★ 210 commit today Go
  3. #3
    smg-project/smg

    Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing,...

    91.1
    Ranks here on 543 GitHub stars and a commit within the last week, plus 75% of issues closed.
    Freshness
    30.8
    Issue health
    23.2
    Stars
    14.0
    Contributors
    12.3
    Description
    6.2
    ★ 543 commit today Rust
  4. #4
    ChronoAIProject/NyxID

    Connect AI agents to any API, anywhere. Securely. Open-source gateway that proxies requests, injects credentials automatically, punches through NAT to reach localhost services, and wraps REST APIs...

    90.2
    Ranks here on a commit within the last week and 92% of issues closed.
    Freshness
    30.8
    Issue health
    28.3
    Contributors
    12.3
    Stars
    8.0
    Description
    6.2
    ★ 36 commit today Rust
  5. #5
    aliang-one/aliangboard

    An open-source, AI-native Kubernetes panel — full multi-cluster management via a Vue 3 + Node gateway, with a built-in Agent workbench and MCP server that lets LLMs read, write, and operate your cl...

    90.0
    Ranks here on a commit within the last week and 100% of issues closed.
    Freshness
    30.8
    Issue health
    30.8
    Stars
    10.5
    Contributors
    7.2
    Description
    6.2
    ★ 110 commit 1d ago JavaScript
  6. #6
    soulteary/owlmail

    OwlMail is a self-hosted, AI-native email testing gateway for developers, CI pipelines, and coding agents. Capture, inspect, wait for, validate, and route application emails through REST, Webhooks,...

    89.1
    Ranks here on a commit within the last week and 100% of issues closed.
    Freshness
    30.8
    Issue health
    30.8
    Stars
    9.6
    Contributors
    7.2
    Description
    6.2
    ★ 73 commit 4d ago Go
  7. #7
    openmake/openmake_llm

    Open-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.

    88.6
    Ranks here on a commit within the last week and 100% of issues closed.
    Freshness
    30.8
    Issue health
    30.8
    Stars
    8.4
    Contributors
    7.9
    Description
    6.2
    ★ 43 commit today TypeScript
  8. #8
    hwdsl2/self-hosted-ai-stack

    Deploy a complete self-hosted AI stack with Docker Compose: Ollama, LiteLLM, AnythingLLM, Whisper, WhisperLive, Kokoro, Embeddings, Docling and MCP Gateway. Local-first, private by default, with li...

    86.4
    Ranks here on a commit within the last week and 100% of issues closed.
    Freshness
    30.8
    Issue health
    30.8
    Stars
    11.3
    Description
    6.2
    License
    4.6
    ★ 158 commit 1d ago Shell
  9. #9
    bitrouter/bitrouter

    The minimal interpretable model router that learns & adapts to your agent workflows

    86.3
    Ranks here on 230 GitHub stars and a commit within the last week, plus 83% of issues closed.
    Freshness
    30.8
    Issue health
    25.6
    Stars
    12.1
    Contributors
    8.9
    License
    4.6
    ★ 230 commit today Rust
  10. #10
    Continuum-AI-Corp/OrcaReplay

    OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

    85.6
    Ranks here on 263 GitHub stars and a commit within the last week, plus 80% of issues closed.
    Freshness
    30.8
    Issue health
    24.6
    Stars
    12.4
    Contributors
    8.9
    License
    4.6
    ★ 263 commit 2d ago TypeScript

More LLM Client MCP Servers

# Tool Score Stars Last Commit Language
11 emaspa/unraidclaw 85.5 46 7d ago TypeScript
12 taichuy/1flowbase 84.8 265 today Rust
13 diegosouzapw/OmniRoute 84.2 70k today TypeScript
14 croit/aiplane 83.0 23 2d ago Rust
15 engasnm111/lnwjud 82.5 190 today TypeScript
16 lianluo-esign/ferrogate 82.2 23 6d ago TypeScript
17 TomLeeLive/openclaw-unity-plugin 82.0 107 16d ago C#
18 gefsikatsinelou/MetaSearchMCP 81.7 58 today Python
19 Yinglianchun/Serein 81.5 68 today Python
20 ankitcharolia/kiro-gateway 81.4 79 3d ago Python
21 agentgateway/agentgateway 81.0 5.0k today Rust
22 soapbucket/sbproxy 80.8 53 14d ago Rust
23 stdapi-ai/stdapi.ai 80.5 25 1d ago Python
24 stellar-experimental/stellar-raven 80.5 8 4d ago JavaScript
25 0xzr/freellmpool 80.5 113 7d ago Python
26 nirholas/plugin.delivery 80.3 25 10d ago TypeScript
27 alifanov/scopegate 79.8 17 11d ago TypeScript
28 ferro-labs/ai-gateway 78.8 265 4d ago Go
29 KochC/opencode-llm-proxy 78.3 67 today JavaScript
30 artcc/openclient-llm 78.1 19 1d ago Swift
31 IBM/mcp-context-forge 77.9 4.5k today Python
32 TomLeeLive/openclaw-godot-plugin 77.3 17 23d ago GDScript
33 perforce/perforce-agentic-gateway 77.1 13 3d ago —
34 barbacane-dev/barbacane 76.9 28 today Rust
35 stabgan/openrouter-mcp-multimodal 75.9 92 1d ago TypeScript
36 unrelated-ai/mcp-gateway 74.7 25 5d ago Rust
37 ypollak2/llm-router 73.9 88 today Python
38 Azure-Samples/AI-Gateway 73.8 990 9d ago Jupyter Notebook
39 cuihuan/awesome-ai-gateway 73.3 115 1d ago HTML
40 archestra-ai/archestra 73.2 4.3k today TypeScript
41 hashangit/openfusion 70.6 35 12d ago TypeScript
42 RelayPlane/proxy 69.6 203 2d ago TypeScript
43 deltawi/deltallm 69.5 19 1d ago Python
44 GhostXia/AIRP 69.5 15 14d ago Rust
45 NateBJones-Projects/OB1 69.2 4.6k 1d ago TypeScript
46 off-grid-ai/OGAD 68.7 113 today TypeScript
47 Shelpuk-AI-Technology-Consulting/lad_mcp_server 68.1 22 1mo ago Python
48 zaber-dev/free-ai-gateway 66.1 16 4d ago TypeScript
49 maximhq/bifrost 65.8 8.3k today Go
50 centralmind/gateway 64.0 548 1y ago Go