Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Explore MITRE CWE weaknesses and CAPEC attack patterns, mitigations, code examples, and mappings via MCP. STDIO or Streamable HTTP.
Node.jsApache-2.0★ 1Few starsNo key
TSUNAGI///Matrix — the BMW E46 M3 tools' calculations as a library, CLI and MCP server: MSS54HP BIN + Testo log → VE and rf_korr corrections, locally. MIT
Node.jsMITFew starsNo key
🚀 Enterprise Multi-Agent Operating Framework: 404 curated production skills & 120 specialized subagents for Antigravity, Claude, and Codex with 70% token compression.
SkillMIT★ 2Few starsNo key
143-tool FL Studio MCP: compose, arrange, mix and analyze audio. 50 plugin profiles, 4,872 named controls and 1,148 qualified mappings. Background control on supported native routes.
PythonMIT★ 2Few starsNo key
Virtual paged attention KV-cache memory manager with logical block mapping, non-contiguous physical page allocation, and zero-copy fragmentation tracking.
SkillMIT★ 7No key
Virtual paged attention KV-cache memory manager with logical block mapping, non-contiguous physical page allocation, and zero-copy fragmentation tracking.
SkillMIT★ 7No key
A self-hosted canvas for mapping how things fit together, where every node is a markdown file you own, and your AI agents can draw on it too.
SkillAGPL-3.0★ 4Few starsNo key
EVM calldata decoding, debug trace revert pinpointing, storage slot layout mapping, and reentrancy auditing.
SkillMITFew starsNo key
Claude Agent Skill that gives Claude expert knowledge of the Esri ArcGIS Utility Network
PythonMITFew starsNo key
MAELIN: graph-native incident response on FalkorDB. Agents find every attack path, prove the minimal cut (algo.maxFlow), replay it on a graph clone, and remember outcomes across sessions. Graph Hacks
SkillApache-2.0★ 2Few starsNo key
Zero-dependency in-memory PII airgap & reversible masking proxy for Cloud LLMs (GDPR Art. 32 compliant MCP server)
SkillApache-2.0★ 4Few starsNo key
Draft-target model speculative decoding verification engine with rejection sampling, acceptance rate telemetry, and dynamic speedup ratio estimation.
SkillMIT★ 8No key
Native C++23 MCP server for PE analysis, process memory, Zydis disassembly, and Win32 debugging.
SkillMIT★ 4Few starsNo key
Draft-target model speculative decoding verification engine with rejection sampling, acceptance rate telemetry, and dynamic speedup ratio estimation.
SkillMIT★ 8No key
High-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).
SkillMIT★ 7No key
High-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).
SkillMIT★ 7No key
Radix trie-based prompt prefix cache optimizer matching longest common prompt token prefixes to eliminate redundant prefill computation and reduce TTFT.
SkillMIT★ 7No key
Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.
SkillMIT★ 7No key
Radix trie-based prompt prefix cache optimizer matching longest common prompt token prefixes to eliminate redundant prefill computation and reduce TTFT.
SkillMIT★ 7No key
Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.
SkillMIT★ 7No key
Static RTTI/call/xref graph of Elden Ring's executable, served to agents over MCP. Mapping layer for an open-source co-op mod.
PythonMITFew starsNo key
BLM mining claims (MLRS) — fleet #2826.
Hosted by authorMITFew starsNo key
Remote MCP server for hotel and travel feed validation, normalization and platform requirement comparison.
Hosted by authorMITFew starsNo key
Virtual Longevity Clinic (VLC): a multi-agent AI research framework for selection intelligence - an auditable choose-monitor-revise loop for person-level intervention selection, built on a 332-module
SkillMIT★ 1Few starsNo key
Who stands behind it