- Conduid
- Marketplace
- #token-efficiency
MCP servers tagged token-efficiency
50 live MCP servers tagged "token-efficiency", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with token-efficiency.
Codeprism
An experimental, 100% AI-generated, high-performance code intelligence server providing AI assistants with a graph-based understanding of codebases.
Cheqd
Model Context Protocol (MCP) Toolkit for cheqd decentralised identity
Agentic Engineering Infrastructure
Deploys your OS, databases, and SSL on your VPS in just 10 minutes. Orchestrates a team of AI agents for coding, marketing, and sales. The built-in optimizer saves up to 90% on to…
Remindb
An agentic memory database that cuts session tokens by 75–99%. One portable SQLite file — your agent's memory, anywhere.
Agent Engineering Infrastructure
Deploys your OS, databases, and SSL on your VPS in just 10 minutes. Orchestrates a team of AI agents for coding, marketing, and sales. The built-in optimizer saves up to 90% on to…
Hedl
Token-efficient data serialization for LLM/AI. 50% fewer tokens than JSON, 93% better value/token. Rust, schema validation, LSP.
IHMT MEMORY
Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files
Agent Coherence
The data integrity layer that stops AI agents from silently corrupting shared state — across sessions, time, and concurrent runs.
Gcf
The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1…
Tokenectomy Razor
Tokenectomy Razor 🗡️ — Autonomous M2M Model Context Protocol (MCP) server & log surgery engine for AI coding agents
Toolkit
Shared MCP server building blocks for @us-all servers — token-efficient by design (category toggles, extractFields, search-tools meta, registry, runtime)
CodePrism
Standalone Python package + MCP server that builds and maintains a persistent knowledge graph of any codebase, exposing precise, token-efficient context to AI coding agents.
Brain
Local-first MCP server that tells coding agents which files to read, and how sure it is. 97% Hit@10 on Java (SWE-bench Multilingual), 89% on Python (SWE-bench Lite), zero LLM cost…
Omnex
Omnex is not a search tool. It is the memory substrate for the agentic era — the data layer that sits beneath AI agents, AI operating systems, and human-AI interaction. What exist…
Tailor MCP
Local-first MCP server for AI analysis of sensitive structured data. Tier-gated access, durable audit log, Wardrobe of cross-session memory — your data stays on your machine.
Toke Local
Zero-dependency MCP server that cuts round-trips and tokens for coding agents: 6 aggregate tools (agent_search, agent_read, agent_edit, agent_exec, agent_git, agent_savings)
Grandpa
Grandpa makes AI coding agents work smarter, not harder. Zero-bloat architecture, 8 skills, CLI scanner, and benchmark harness for 25+ AI agents.
Skillstate
O(1) prompt footprint for long-horizon agents. The SKILL.state paper (arXiv:2608.26263) reimplemented — eq. 8 reproduces exactly, 82.5x at 60 files. 100% coverage.
Tailor MCP
Local-first MCP server for AI analysis of sensitive structured data. Tier-gated access, durable audit log, Wardrobe of cross-session memory — your data stays on your machine.
Sweepspace
Build big. Spend less. A desktop workspace for AI coding agents: run Claude Code, Codex and Gemini side by side with 9.3x fewer tokens.
Cdc
Convert MCP servers into Claude Code skills — not MCP connections. Token-minimal, code-execution pattern.
Rag Runtime Kernel
Persistent memory and deterministic state control for any LLM, in two tiers. Tier 1: a single markdown spec you paste into any chat - no install. Tier 2: a formally-verified Pytho…
Agent Native Format
Token-minimal system views for AI agents. Translate Kubernetes and live state into compact Agent Native Format with Go tooling and governed execution primitives.
Myelin
The neural insulation layer for AI coding agents. 93% token reduction, 6× longer sessions. Serena + Semble + Headroom + RTK + mem0 in one installer.
Tokenhub
Production-packaged MCP server for coding agents that keeps the public tool surface small while routing file, git, web, database, package, browser, GitHub, and Sentry work through…
Gcf Kotlin
GCF Kotlin implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Typesafe MCP
MCP server for TypeSafe AI's Jev: typed yes/no, choice and score answers with act / review / abstain gating.
Laya Engine
Локальный движок типизированных решений (choice/score/noul) на Go + ONNX Runtime: ~322M параметров, один forward pass на батч вопросов, GPU/CPU, без Python в рантайме. Плагин и на…
McpMux
Dynamic MCP multiplexer — one gateway, many upstream MCP servers.
Qarinah
Qarinah is evidence-linked project memory for coding agents - compact enough to save context, inspectable enough to trust.
Dotnet Toolkit
AI-native .NET code intelligence for faster, more accurate codebase navigation with lower token usage.
Capsule
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
Gcf Rust
GCF Rust implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Gcf Python
GCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Gcf Go
GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Furl Ctx
Context compression for AI agents — cut token usage costs with retrievable CCR compression. Rust core + Python API, Claude Code & Codex plugin, MCP server. PyPI: furl-ctx
Gcf Typescript
GCF TypeScript implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Gcf Swift
GCF Swift implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Tree Sitter Gcf
Tree-sitter grammar for GCF. Full spec compliance, WASM build for browser playground.
Urusilla
Open AI-agent interoperability research. Bring your own agent, complete verified public work, and earn contribution credit; if URSL launches, 1 credit = 1 URSL.
Axiolex
Shared tool discovery and execution for AI clients and applications across MCP, A2A, and internal tools—intent-ranked Top-K retrieval with centrally managed provider and tool chan…
Mugil Ide
Token-efficient autonomous AI IDE — a browser-based coding agent with an xterm.js terminal, smart caching, automatic model routing, and MCP tooling. Minimizes token cost while max…
Claude Token Efficient Setup
A tested setup guide and prompt workflow for pairing Claude Desktop with code-review-graph and filesystem MCP on macOS — for token-efficient AI-assisted development on large codeb…
Tokenectomy
Autonomous M2M MCP server that scrubs framework noise & redacts secrets from AI agent error logs before they hit your context window
Betterthantoon
GCF vs TOON benchmark data
Memorycore AI For Codex
MemoryCore Ai - For Codex: persistent memory via MCP with a 24-hour idle window for delayed memory consolidation, TurboVec semantic search and source-checked context to reduce tok…
Gcf Vscode
VS Code syntax highlighting for GCF, the AI-native wire format for structured data. 71% fewer tokens than JSON.
Graphscout
Cached, incremental code-graph maps so AI agents query code structure instead of reading whole files. CLI + MCP, wires into Claude Code, Codex, Gemini CLI, Cursor. Auto-sync watch…
Pare
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
Betterthanjson
No description published.