terse
Related Servers
Alternatives to terse
- AlicenseAqualityBmaintenanceEnables encoding JSON into compact TOON format and decoding TOON back to JSON, reducing token usage for LLM prompts.213Apache 2.0
Related Servers
- AlicenseAqualityAmaintenanceMCP server and local proxy that compresses LLM prompts, tool output, and replies to cut token cost, with a quality gate that reverts any step that does not save. Exposes llmtrim_compress, llmtrim_compress_text, and llmtrim_stats.3229Mozilla Public 2.0
- AlicenseAqualityBmaintenanceMCP 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.54MIT
- FlicenseBqualityCmaintenanceLocal 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.5-
- AlicenseAqualityAmaintenanceAggregator MCP proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery, and compresses large tool outputs (HTML→Markdown, JSON summarization) with full-output retrieval via read_more and a per-session token-savings report.464 npm2MIT
- AlicenseNot gradedqualityCmaintenanceA local-first MCP server that reduces LLM token usage by intercepting, deduplicating, compressing, and optimizing MCP tool calls and responses.1 npmMIT
- AlicenseAqualityBmaintenanceAn 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.84MIT
TDQS
Scored across 2 tools
The two tools are completely distinct: demo_orders returns a JSON array of records, while demo_logs returns plain-text log lines. Their purposes—showing structured vs. text output—are clearly separated, leaving no ambiguity.
Both tools follow the same `demo_<plural noun>` pattern, using consistent lowercase snake_case and a common prefix. The naming is predictable and coherent, even though it deviates from a strict verb_noun style.
At just two tools, the server is slightly below the typical 3-15 range, but the count is deliberate: one tool for each of terse's two data tiers. This makes the set well-scoped for its demo purpose.
The server's stated domain is demonstrating terse's handling of record-shaped vs. text-shaped results, and these two tools cover exactly that distinction. There are no missing operations or dead ends for the intended scope.