Skip to main content
Glama
deenesjakoruzh
ral197979

Ava MCP Adapter

by ral197979
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Ava MCP 适配器

轻量级 REST 桥接器，实现了 JarvisEPC 的 MCP 工具服务器契约（GET /tools、POST /execute、GET /health），并将每个工具代理到部署在 https://ava-agent-qzmu.onrender.com 的 Ava_Agent，进而路由到 CommandDeck 专家大脑。

为什么需要它

JarvisEPC 的 api/routes/mcp.ts 期望的是 REST 工具服务器形态。现有的 Ava_Agent 使用的是 FastAPI 领域特定端点（/chat、/projects/.../tasks、/broadcast、/v1/skills/invoke 等）——此适配器就是将 REST 契约映射到这些端点的粘合剂。

Related MCP server: Bridge MCP Server

公开的工具

名称

类别

上游

ava_chat

AI

POST /chat → CommandDeck 大脑路由

ava_status

系统

GET /status

ava_projects_list

系统

GET /projects

ava_task_submit

AI

POST /projects/{id}/tasks

ava_broadcast

AI

POST /broadcast

ava_memory_recall

AI

POST /projects/{id}/memory/recall

ava_memory_summary

AI

GET /projects/{id}/memory

ava_skill_invoke

AI

POST /v1/skills/invoke

ava_git_status

系统

GET /projects/{id}/git/status

ava_git_log

系统

GET /projects/{id}/git/log

ava_git_commit

系统

POST /projects/{id}/git/commit

部署

已通过 render.yaml 连接到 Render。在 Render 仪表板中设置 AVA_AGENT_API_KEY（从 Ava_Agent 服务环境变量中复制）。

将 AVA_MCP_URL=https://ava-mcp-adapter.onrender.com 配置到 JarvisEPC 服务环境变量中；MCP 选项卡将从“Ava offline”切换为显示完整的合并工具目录。

This server cannot be deployed

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Bridge MCP Server

    queenamara
    F
    license
    Not graded
    quality
    Not graded
    maintenance
    Bridge is a hosted MCP server that connects AI models to business tools like ClickUp and a repository of pre-built workflow skills. It enables direct interaction with project management tools and automated instruction sets through natural language.
    -

  • rest-to-mcp

    viktormarinho
    A
    license
    Not graded
    quality
    D
    maintenance
    A bridge that enables any LLM to access and interact with documented REST APIs through the Model Context Protocol (MCP).
    7 npm
    6
    MIT

  • mcp-proxy

    dyy-fq
    A
    license
    Not graded
    quality
    D
    maintenance
    Bridges LLM clients with existing RESTful microservices by converting MCP tool calls into REST requests, enabling any REST API to be used as an MCP tool without modifying the microservices.
    805,191 npm
    1
    MIT