- Conduid
- Marketplace
- #token-optimization
MCP servers tagged token-optimization
299 live MCP servers tagged "token-optimization", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with token-optimization.
WindowsJev
Token-efficient Windows automation and durable research MCP server for Codex and Claude Code, powered by TypeSafe Jev.
Jev Compactor
Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.
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.
Claude Context Saver
MCP server that cuts Claude Code token usage: log compression (builds/tests/installs) + smart file reading (symbol-level source access via tree-sitter).
Chronofact
⚡ ChronoFact: 4-Pillar Epistemic AI Backbone. Real-time temporal cutoff calibration, active NLI claim verifier, zero-pollution memory, and mcplex TF-IDF cost optimizer.
Context Engine
Drop-in token saver for Claude Code & MCP agents — auto-rewrite hooks + 10-tool MCP server + BM25/PageRank repo maps + call graphs in 7 languages + local RAG. Single Rust binary,…
Multiplexer
One MCP server fronting many: list_servers, list_tools, search_tools, describe_tool, call_tool, refresh_tools, authorize_server. Lazy schema discovery slashes context-token costs.…
Ctxvitals
A Lighthouse for your AI agent stack — measures the real token cost of MCP servers, skills, and rules; flags security issues and duplicates; grades your setup A-F.
Agent MemGC
⚡ High-performance linter, cache-layout optimizer, and garbage collector for AI agent instruction files (AGENTS.md, CLAUDE.md, .cursorrules) in Rust.
Cortex
An Obsidian-style vault your AI agents can read — and an orchestrator that lets a cheap model write while your expensive model only reviews.
Allan MCP Memory Code
Store persistent knowledge graphs for AI coding assistants using a local Docker setup with hybrid search and entity extraction.
Polyglot
Write in your native language, Claude Code responds in English. Local-GPU translation + multi-layer anti-bypass enforcement. ~18% tokens saved on Polish, ~43% on CJK.
Top
top for your agent's context window, profile MCP tool-definition token cost vs actual usage from local transcripts and get a safe prune list.
Contextpulse MCP
Real-time MCP server that tracks context budget, detects agent loops, and alerts before token overflow — for Claude Code, Cursor, and any MCP-compatible AI tool.
Claude Local Stack
Claude Code stack for Apple Silicon — multi-profile LLM routing (local MLX, Bedrock, Anthropic), token compression, MCP integration
Slm Gate
Decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs. Intercepts, distills, and routes prompts locally with Ollama to cut token costs and protect monthly qu…
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.
Kosh
Kosh is a token elimination and context efficiency platform for AI agents, reducing context retransmission through leasing, batching, and reusable references.
Claude Context Governor
The control plane for Claude Code. Run a dozen MCP servers and a hundred skills. Pay context for only the ones doing work right now.
Agent Sentry
An enterprise-grade AI Gateway Proxy securing autonomous agents. Features MCP-Guard (an AST-based containment firewall and Docker sandbox blocking 100% of subshell injections) and…
Context Zero Engine
Local code-intelligence engine for AI agents — indexes a repository into a PostgreSQL code graph and serves token-budgeted context (symbols, effects, contracts, blast radius, simi…
Coreball
Semantic context compiler for LLM coding agents — packs the smallest useful codebase context for any task. Zero dependencies, deterministic, token-efficient.
Jev Codex Workbench
Codex plugin and MCP server for TypeSafe Jev decisions and recoverable context reduction, with optional local Laya-MLX and token/time measurement tools.
Lookaberry
Autonomous, headless AI Go-to-Market (GTM) outbound engine & MCP Server powered by PostgreSQL 16 + pgvector.
Repodigest MCP
A local Model Context Protocol (MCP 2.x) server exposing RepoDigest's AST signatures, call graphs, and token-budgeted context packing to AI coding assistants.
Quitegoodproject
The Quite Good Project — Suite of high-speed developer primitives, sub-second headless APIs, and low-token MCP servers for autonomous AI agents.
AI Coding Context Optimizer
Token and context optimization for AI coding agents with smart compression, retrieval, recovery, routing, and MCP integrations.
Gcf Kotlin
GCF Kotlin implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Mrcp Engine
Deterministic AST code-intelligence engine for AI agents — MCP server + REST API for architecture analysis, security audits, and doc generation.
Hermes Self Evolution
🧬 Zero-dependency self-evolution for LLM agents. One file + one prefill = Agent learns from corrections forever. No databases, no APIs, no overengineering.
Model Sherpa
Stop hallucinated tool calls, break looping behaviour, and keep secrets out of your context window — zero-config guide-rails for Hermes Agent.
Map Standard
Estándar declarativo que acota el contexto, limita las herramientas y capa el coste de un modelo por tarea. Disciplina enforzada por código, no agentes.
Jettison
Token optimizer for AI coding agents. Repo map, read pruning, prose compression — client-side, no proxy. 20-25% fewer turns, measured by live A/B. Verify it on your own repo.
Tokenmarkdown
Sub-150ms Web-to-AST Markdown engine & Model Context Protocol (MCP) server. Eliminates 90%+ raw HTML token bloat for LLMs, RAG, and agent context.
Context Guardian
Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine.
Tool Visibility Controller
Claude Code plugin for per-agent tool visibility — hide and refuse subagents, skills, MCP and built-in tools per loop
Jevto
Command-output selection for coding agents, with exact local recall and optional Jev ranking.
Code Mode
🤖 Enable AI code generation using the Code Execution MCP Server, integrating large language models with the Model Context Protocol for seamless tool use.
Conductor
97% fewer tokens. Parallel MCP execution through a sandboxed Deno runtime.
Terse
Terse — an AI-native code language: a machine-designed, token-dense format for AI coding agents. Open source, Apache-2.0.
Mnemex
Anchored memory MCP server for AI coding agents — binds decisions to code symbols, delivers context just-in-time. Works with Claude Code, Codex CLI, Cursor, Windsurf, Gemini CLI.…
Cursor Token Saver
A cognitive layer for AI coding agents: content-addressed evidence store for lossless token savings; verifiable semantic memory + project world model + skill runbooks. Fully local…
Token Optimizer
Smartest context aware Token Optimizer for mcp tools.
Token Saver
Detect and reduce wasteful AI token usage by warning on large outputs, verbose logs, and repeated history in MCP-compatible clients.
inth3shadows/terse
<server>`
Tool Search
MCP proxy server — 85-96% token savings via lazy tool loading & fuzzy search across 100+ MCP servers. npm i mcp-tool-search
Cortex Works Minimal
A hyper-optimized MCP server that supercharges AI coding agents. Outperforms built-in IDE tools with AST-based precision editing and native OS control, drastically reducing LLM to…
Serena Slim
serena MCP (38% less tokens). Quick setup: npx serena-slim --setup
Memory Slim
memory MCP (44% less tokens). Quick setup: npx memory-slim --setup
Sequential Thinking Slim
sequential-thinking MCP (0% less tokens). Quick setup: npx sequential-thinking-slim --setup