Related Servers

No user-submitted related servers found.

Related Servers

• Headroom Mini

  lea-blum

  F

  license

  B

  quality

  C

  maintenance

  Local MCP server for token optimization, providing tools to compress code/JSON, optimize prompts, and manage placeholder-based content redaction and hydration to reduce LLM token usage.

  Updated 2 months ago (2026-06-30 11:48 UTC)

  5

• slimtoken

  greyok00

  A

  license

  A

  quality

  B

  maintenance

  An MCP server that exposes token-optimization pipeline functions as tools, enabling MCP-compatible hosts to reduce token usage in requests before they are forwarded to an Anthropic-compatible backend.

  Updated 9 days ago (2026-08-17 07:16 UTC)

  8

  4

  MIT

• Compendium

  hocestnonsatis

  A

  license

  -Not graded

  quality

  A

  maintenance

  MCP server that minimizes LLM token usage by compressing, summarizing, filtering, chunk-referencing, and pruning large context before it reaches the model, with heuristic or local-SLM smart actions, caching, and token counting.

  Updated 13 days ago (2026-08-13 04:18 UTC)

  720

  MIT

• mcp-compressor

  atlassian-labs

  A

  license

  -Not graded

  quality

  A

  maintenance

  A proxy server that wraps existing MCP servers to significantly reduce token consumption by compressing tool descriptions into a two-step interface. It enables users to integrate extensive toolsets without exceeding context limits or incurring high API costs.

  Updated a month ago (2026-07-28 03:40 UTC)

  106

  Apache 2.0

• Refract

  LoudiliMed

  A

  license

  A

  quality

  B

  maintenance

  MCP proxy that compresses tool schemas on the fly. Up to 98% token reduction, 100% signal preserved verified after every compression. Zero LLM calls, fully deterministic.

  Updated 10 days ago (2026-08-15 17:47 UTC)

  5

  3

  MIT

• clair

  concensure

  F

  license

  -Not graded

  quality

  D

  maintenance

  An MCP server that reduces token usage by lazily loading skills and tools only when needed, and routing repetitive subtasks to ML backends instead of the LLM.

  Updated 5 months ago (2026-03-12 22:39 UTC)