Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
bifrost
MCP serversOpen-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
git clone https://github.com/maximhq/bifrost.git -
CacheBoost
MCP serversWarm CDN and reverse-proxy caches: manage sites, run warms, read cache-hit stats.
-
token-optimizer-mcp
MCP servers91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
git clone https://github.com/ooples/token-optimizer-mcp.git -
cache
MCP serversCache headers, CDN, LRU simulation for AI agents
@rog0x/mcp-cache-tools@1.0.2 -
Fresh cache hint
MCP serversFresh cache hint
-
cache-proxy
MCP serversLLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.
-
Prompt-cache prefix guardian
MCP serversCache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.
-
cacheport
MCP serversKey-value cache over Redis: set, get, delete and list keys.
@reneturcios/cacheport@0.1.0 -
cacheoverflow
MCP serversMCP server for cache.overflow - AI agents sharing knowledge with AI agents
cache-overflow-mcp@0.5.5 -
Cache-Control max-age shape
MCP serversCache-Control max-age shape
-
dns-cache
MCP serversDNS/WHOIS/SSL/geo-IP cache MCP server for AI agents.
@weiseer/dns-cache-mcp@0.1.1 -
Cache-Control token count, value discarded
MCP serversCache-Control token count, value discarded
-
Execute cdn-cache-warmup-agent-mcp
MCP serversPremium agentic endpoint for cdn-cache-warmup-agent-mcp.
-
cve-cache
MCP serversRecent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go).
@weiseer/cve-cache-mcp@0.1.1 -
Semantic Cache MCP
MCP serversFile cache for coding agents: re-reads cost ~40 tokens, changed files return diffs.
semantic-cache-mcp@0.7.0 -
cachemiss
MCP serversCI cache-miss analysis: which hashed key inputs changed and why runs missed or fell back.
@reneturcios/cachemiss@0.1.0 -
nextjs-cache-handler-mcp
MCP serversInspect and operate Next.js Redis caches: health, tag state, SWR simulation, safe invalidation.
@leejpsd/nextjs-cache-handler-mcp@0.1.2 -
build-cache-mcp
MCP serversSummarize local build and cache footprint using size and age buckets without returning paths or...
build-cache-mcp@1.0.1 -
High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation
https://github.com/Alpha-Park/genpark-vector-embedding-cache-deduplication-sentinel-skill/releases/download/v1.0.1/genpark-vector-embedding-cache-deduplication-sentinel-skill.mcpb -
Cache Key Explosion Auditor
MCP serversAudits a sample of HTTP request URLs against explicit, documented cache-key standardization rules...
-
cachetank-mcp
MCP serversCacheTank MCP server gives every AI tool your personal context so you never start from zero.
cachetank-mcp@2.1.2 -
VectorCache Semantic Vector Cache
MCP serversx402-gated semantic vector cache for agent swarms: Redis-backed similarity lookup. Paid in USDC.
@nodeproxy/vectorcache@0.1.1 -
Catalog-cache guard for agent tool catalogs
MCP serversCache guard: forced-private partitioning, TTL clamp, fingerprint diffing, exposure verdicts.
-
vmlx
MCP serversvMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm
git clone https://github.com/jjang-ai/vmlx.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.