Skip to main content
Glama
Agent Context Token Optimizer MCP Server

Agent Context Token Optimizer MCP Server

by DeathOVOGod

Agent Context Token Optimizer v2

English | 中文

English

A local-first, dependency-free core for replacement-history compaction and an owner-bound secure tool-output vault, with honest adapters for multiple agent ecosystems.

Capability matrix

Target

History

Vault

Mode / boundary

Hermes Agent

policy helper / explicit host patch point

automatic allowlisted transform hook + retrieval tool

History: integration helper; Vault: Native plugin

OpenAI-compatible/custom

Python message helper

explicit middleware helper

Native helper when the application controls messages/tool results

LangChain / LangGraph

duck-typed conversion + state helper

compose the core helper in a tool wrapper

Native helper; this package does not patch framework internals

AutoGen

message-list helper

compose a tool wrapper

Native helper only at application-owned hooks

CrewAI

task-context handoff

compose a tool wrapper

Wrapper; no claim of private transcript mutation

Claude Code

new/resumed-session JSON handoff

explicit MCP tools

Wrapper + MCP-only; cannot rewrite existing history or automatically intercept output

Codex CLI

new/resumed-session JSON handoff

explicit MCP tools

Wrapper + MCP-only; cannot rewrite existing history or automatically intercept output

OpenCode

new/resumed-session JSON handoff

explicit MCP tools

Wrapper + MCP-only; cannot rewrite existing history or automatically intercept output

MCP caveat: text passed explicitly to store_tool_result normally already entered the host/model context. MCP provides owner-bound retention and retrieval, not retroactive token savings or automatic interception.

Install and run

python3 -m pip install .
context-token-optimizer install-hermes-plugin
python3 -m token_optimizer.cli compact --agent claude-code < handoff.json
TOKEN_OPTIMIZER_OWNER='<host-generated-opaque-id>' \
  python3 -m token_optimizer.mcp_server --store ~/.context-token-optimizer/vault
python3 -m pytest -q

Never let the model choose the MCP process owner. Generate/bind it in host configuration. See Integration, Architecture, Verification, and Changelog.

Safety contract

Latest real user intent remains last; summaries are reference-only. Vault artifacts use hashed owner binding, strict IDs/types, sensitive-content rejection, SHA-256 integrity, 0700 directories, 0600 files, atomic writes, TTL checks on read and cleanup, and a total quota. These controls reduce risk but do not make retained untrusted content safe to execute.

Related MCP server: Mycelia

中文

v2 提供本地优先、无第三方运行时依赖的替换历史压缩核心和绑定 owner 的安全工具输出仓库,并为多种 Agent 生态提供不夸大能力的适配器。

能力矩阵

目标

历史压缩

输出仓库

模式 / 边界

Hermes Agent

策略 helper / 显式宿主补丁点

白名单自动 transform hook + 取回工具

历史:集成 helper;Vault:Native 插件

OpenAI-compatible/custom

Python 消息 helper

显式 middleware helper

应用控制消息和工具结果时为 Native helper

LangChain / LangGraph

鸭子类型转换 + state helper

在工具 wrapper 中组合 core

Native helper;不修改框架内部

AutoGen

消息列表 helper

组合工具 wrapper

仅限应用可控 hook 的 Native helper

CrewAI

task-context handoff

组合工具 wrapper

Wrapper;不声称修改私有历史

Claude Code

新建/恢复会话 JSON 交接

显式 MCP 工具

Wrapper + MCP-only;不能原地改历史或自动截获输出

Codex CLI

新建/恢复会话 JSON 交接

显式 MCP 工具

Wrapper + MCP-only;不能原地改历史或自动截获输出

OpenCode

新建/恢复会话 JSON 交接

显式 MCP 工具

Wrapper + MCP-only;不能原地改历史或自动截获输出

**MCP 限制:**显式传给 store_tool_result 的正文通常已经进入宿主/模型上下文。MCP 只提供绑定 owner 的保存和取回,不代表自动拦截或追溯性节省 Token。

安装与命令同上。MCP owner 必须由宿主生成并通过进程参数/环境绑定,不能让模型传入。安全措施包括 owner 哈希绑定、严格类型与 ID、敏感内容拒绝、SHA-256、原子写、0700/0600 权限、读取时 TTL 和总配额;仓库内容仍应视为不可信数据。

License / 许可证

MIT; third-party projects retain their licenses and copyrights. / MIT;第三方项目保留其许可证与版权。

Available Tools

2 tools
read_omitted_contentC

Read one bounded page from this process owner's local vault.

Inputs: content_id (required), limit, offset.

store_tool_resultB

Explicitly store non-sensitive text in this process owner's local vault. Supplied text may already count toward host context.

Inputs: content (required), tool_name (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one stores text, the other reads a stored page. No overlap.

    Naming Consistency5/5

    Both tool names follow a consistent verb_noun pattern: store_tool_result and read_omitted_content.

    Tool Count3/5

    With only 2 tools, the server feels minimal but could be acceptable for a narrowly focused functionality. It is borderline.

    Completeness2/5

    Missing essential operations like deleting, updating, or listing stored content, which are needed for full lifecycle management.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI memory persistence and secure credential management via vault tools for MCP-compatible clients like Claude Desktop, Cursor, and VS Code.
      12
      6 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides a persistent, cross-tool memory layer for AI coding agents via MCP, enabling storage and retrieval of decisions, preferences, and context across different tools and models.
      1
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      MCP-native persistent memory for AI agents. Stores and retrieves encrypted memories with Trust Quotient scoring, cross-agent handover protocol, and immutable audit trail. 13 tools. Remote endpoint available.
      13
      20 PyPI
      13
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables agents to access a shared portable vault for memory, skills, and API credentials through MCP, so tools can store and retrieve memories, read versioned skill playbooks, and make server-side API calls without exposing secret keys.
      Apache 2.0