AegisForge MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AegisForge MCP Servercheck agent health and classify the latest failure"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AegisForge
AegisForge is an agent operating system control plane for coding-agent execution, failure intelligence, adaptive sandbox policy, evaluation, and experience memory.
Production surfaces
Frontend dashboard: Vite + React, deployed as a Vercel static build.
MCP server: Streamable HTTP-compatible JSON-RPC endpoint at
/mcp(implemented byapi/mcp.ts).Health: call the
aegis_healthMCP tool.Tools:
aegis_health,run_agent_step, andclassify_failure.
Related MCP server: linkyun-ops-mcp
Local development
npm install
npm run devThe dashboard runs on port 3000. The MCP handler is available through Vercel's local runtime with vercel dev.
Vercel deployment
Import this repository into Vercel with the project root set to the repository root. The included vercel.json builds the dashboard and rewrites /mcp to /api/mcp.
Optional environment variable:
GEMINI_API_KEY=...The current MCP tools use deterministic safe responses so the server remains usable without credentials. A subsequent worker deployment can replace the deterministic adapter with the real Rust sandbox and queue services.
MCP smoke test
After deployment, send an initialize request to https://YOUR_DOMAIN/mcp, then call tools/list and tools/call using JSON-RPC 2.0.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.
Discover and call AI agents via MCP. Supports A2A agents and platform agents with async tasks.
Agent-driven search: build, import, tune, search, and score result quality — all over MCP.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables LLMs to inspect and test other MCP servers by listing and calling their tools, reading resources, and getting prompts. Supports stdio, SSE, and HTTP transports for both local and remote MCP server inspection.71381MIT
- FlicenseBqualityBmaintenanceProvides MCP tools for querying LinkYun operations metrics, including listing metrics, querying metrics, managing agents, and home recommendations, by forwarding requests to the LinkYun Agent Ops HTTP API.15
- AlicenseNot gradedqualityFmaintenanceProvides utilities to help maintain MCP repositories, including testing tools, parameter type support, and multiple transports (STDIO, SSE, Streamable HTTP).169MIT
- AlicenseAqualityBmaintenanceProvides a JSON-RPC MCP server that exposes policy-governed agent tools, including paid tools, tool muxing, and OpenAPI-to-MCP conversion, enabling agents to discover, coordinate, and execute tasks within the ProtoOS ecosystem.51Apache 2.0
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Himanshu90909/AgesForge'
If you have feedback or need assistance with the MCP directory API, please join our Discord server