MCP server Claude CodeCodexCursor +2
MCP server "codebase-memory-mcp" as configured in suyoumo/ClawProBench. Launched with codebase-memory-mcp.
not rated 827
+3 1mo ago A
tokens not measured
original Apache-2.0
unreal-mcp
02MCP server Claude CodeCodexCursor +2
MCP server "unreal-mcp", hosted remotely at 127.0.0.1, as configured in ukanwat/aaabench.
not rated 385 2mo ago A
tokens not measured
original MIT
malicious
03MCP server Claude CodeCodexCursor +2
One of 4 in claude_desktop_config.json
MCP server "malicious" as configured in AIS2Lab/MCPSecBench. Launched with uv --directory /usr/games/mcp/MCPSecCode/mcpbench run maliciousadd.py.
not rated 40
+1 7mo ago A
tokens not measured
original MIT
MCP server Claude CodeCodexCursor +2
Measured latency, time to first token and uptime for 45 AI inference APIs, by region. Remote server at llmlatency.dev.
not rated 12 2d ago A
tokens not measured
original MIT
mcp-docs
05MCP server Claude CodeCodexCursor +2
The MCP documentation itself, served as an MCP server: lets the agent search the protocol spec and guides. Remote server at modelcontextprotocol.io.
not rated 9
+1 2mo ago A
tokens not measured
copy · 100% Apache-2.0
MCP server Claude CodeCodexCursor +2
Live, neutral benchmarks for public RPC latency, oracles, bridges, perp DEX, and prediction markets. Remote server at openchainbench.com.
not rated 8 yesterday A
tokens not measured
original MIT
metrillm
07MCP server Claude CodeCodexCursor +2
Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client. Runs locally from the metrillm-mcp npm package.
not rated 8 4mo ago A
tokens not measured
original Apache-2.0
intentforge
08MCP server Claude CodeCodexCursor +2
Intent-preserving deterministic CAD pipeline for editable, validated CadQuery models. Runs locally from the intentforge Python package.
not rated 5 2mo ago A
tokens not measured
original Apache-2.0
everything
09MCP server Claude CodeCodexCursor +2
MCP server that exercises all the features of the MCP protocol. Runs locally from the @modelcontextprotocol/server-everything npm package.
not rated 5 4mo ago A
tokens not measured
copy · 89% MIT
MCP server Claude CodeCodexCursor +2
MCP server "agora-memory-toolkit" as configured in DanceNitra/agora. Runs locally from the agora-memory-toolkit Python package.
not rated 3 5d ago A
tokens not measured
original MIT
playwright
11pleasedodisturb/web-agent-comparison
MCP server Claude CodeCodexCursor +2
One of 7 in .mcp.json
MCP server "playwright" as configured in pleasedodisturb/web-agent-comparison. Launched with playwright-mcp.
not rated 2 27d ago A
tokens not measured
original MIT
codex
12MCP server Claude CodeCodexCursor +2
MCP server "codex" as configured in SSC-STUDIO/Ai-Model-Gateway. Launched with codex mcp-server. Needs 1 environment variable to run.
not rated 2 1mo ago A
tokens not measured
original MIT archived
memtrust
13MCP server Claude CodeCodexCursor +2
Independent, reproducible benchmark harness for agent-memory backends (MemPalace, Mem0, Zep/Graphiti, OpenViking): runs LongMemEval, LoCoMo, contradiction-detection, and a dozen other evals against all four and publishes the raw logs, not vendor-curated numbers. Runs locally from the memtrust-cli Python package.
not rated 2 21d ago A
tokens not measured
original Apache-2.0
AiAgentKarl/llm-benchmark-mcp-server
MCP server Claude CodeCodexCursor +2
MCP Server for LLM comparison, benchmarks, and pricing — find the best model for any task. Runs locally from the llm-benchmark-mcp-server Python package.
not rated 1 6mo ago A
tokens not measured
original MIT
sudo-ai-git/mcp-benchmark-hygiene
MCP server Claude CodeCodexCursor +2
MCP server detecting pytest config-leakage that corrupts agent-benchmark grading (deterministic, no-LLM). Runs locally from the mcp-benchmark-hygiene Python package.
not rated 0 1mo ago A
tokens not measured
original MIT
MCP server Claude CodeCodexCursor +2
Measured share of answer for 20 SaaS brands. An open dataset, not an audit of your site. Remote server at dabyte.ai.
not rated 0
changed yesterday A
tokens not measured
original MIT
arena
17MCP server Claude CodeCodexCursor +2
Score AI trading agents against 2,048 coin-flipping monkeys. Public leaderboard. Remote server at api.oaia.fun.
not rated 0 3d ago A
tokens not measured
original MIT
inferbench
18MCP server Claude CodeCodexCursor +2
Vendor-neutral local-LLM-inference benchmark and hardware-config advisor for omlx and llama.cpp -- measures real tokens/second on your own hardware, live. Runs locally from the inferbench-cli Python package.
not rated 0 7d ago A
tokens not measured
original Apache-2.0
MCP server Claude CodeCodexCursor +2
Vendor-neutral CLI and MCP server that verifies the token and cost savings AI-coding-agent context-reduction proxies (rtk, headroom) actually deliver, measured against a real 23-task labeled corpus with a local tokenizer instead of the proxy's own claimed. Runs locally from the tokentrust-cli npm package.
not rated 0 2d ago A
tokens not measured
original Apache-2.0
snipara
20MCP server Claude CodeCodexCursor +2
Hosted MCP for source-backed project context, memory, code impact, and agent workflow continuity. Remote server at api.snipara.com.
not rated 0 5d ago A
tokens not measured
original Apache-2.0
perf
21MCP server Claude CodeCodexCursor +2
Benchmark, memory, Big O analysis for AI agents. Runs locally from the @rog0x/mcp-perf-tools npm package.
not rated 0 6mo ago A
tokens not measured
llmtest-mcp
22MCP server Claude CodeCodexCursor +2
Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models. Runs locally from the llmtest-mcp npm package. Needs 1 environment variable to run.
not rated 0 4mo ago A
tokens not measured
original MIT
mcp-llm-eval
23MCP server Claude CodeCodexCursor +2
MCP server that packages LLM evaluation gates as reusable CI/CD primitives. Runs locally from the mcp-llm-eval Python package.
not rated 0 5mo ago A
tokens not measured
original MIT
MCP server Claude CodeCodexCursor +2
MCP server "mcp-tournament" as configured in samalbanese/mcp-tournament. Runs locally from the mcp-tournament npm package. Needs 1 environment variable to run.
not rated 0 14d ago A
tokens not measured
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: