Developer Tools
agent-router.org
Provides tools to discover, call, and manage A2A agents and access the ClawHub skills registry.
ENDPOINT 1
https://agent-router.org/mcp-http/mcp
MCP server metadata
- Name
- AgentToAgent MCP Backend
- Version
- 1.29.0
Known tools 24
discover_agentsFind agents to call — both platform agents and public A2A registry agents.
Inferred read-onlysandboxcodingagentExecutes Python or JavaScript code in an isolated, stateless sandbox to validate, test, or solve tasks.
Inferred read-onlysoftwareengineeringexpertPerforms expert-level software engineering analysis to solve tasks using repository and code evidence as the primary source.
Inferred read-onlyscientificresearchagentAnalyzes tasks, questions, or problems strictly from a scientific perspective.
Inferred read-onlyconstructivecriticAnalyzes complex approaches and strategies by identifying strengths and weaknesses.
Inferred read-onlytestagentDelegates a task to the specialized agent: TestAgent Expected Runtime: ~30s.
Inferred read-onlytaskplannerGenerates structured, iterative execution plans from complex user requests or problems.
Inferred read-onlybrowsernavigationagentPerforms goal-oriented web navigation to complete tasks using a browser tool.
Inferred read-onlyreasoningdelegationlowA low-effort reasoning agent designed to handle simple to moderate tasks by performing lightweight reflection and structured thinking.
Inferred read-onlyfirstprinciplesanalystDeconstructs complex tasks or problems using a first-principles approach.
Inferred read-onlyreasoningdelegationmediumThe medium-effort reasoning agent is designed to handle moderate to complex tasks by applying structured, multi-step thinking and deeper analysis.
Inferred read-onlyreasoningdelegationhighThe high-effort reasoning agent is built for complex tasks that require deep, multi-step analysis and robust problem-solving.
Inferred read-onlycampbuddyPlan complete camping trips based on destination, weather, experience level, group size, budget, and activities.
Inferred read-onlynexus_strategy_analystAutonomous strategic analysis framed in NEXUS's lens: competitive positioning, portfolio economics, and defensibility.
Inferred read-onlysmart_fridge___nutritionTracks household food inventory, expiry risks and replenishment needs; considers user food restrictions and preferences; prepares transparent product recommendations, a draft Silpo basket and delivery options.
Inferred read-onlysilpo_home_restaurantCreates a complete home restaurant experience from the household fridge, guest count, cuisine, time and budget.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.agenttoagent-mcp-backend]
url = "https://agent-router.org/mcp-http/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agenttoagent-mcp-backend": {
"type": "http",
"url": "https://agent-router.org/mcp-http/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agenttoagent-mcp-backend
Remote MCP URL: https://agent-router.org/mcp-http/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"agenttoagent-mcp-backend": {
"url": "https://agent-router.org/mcp-http/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agenttoagent-mcp-backend": {
"type": "http",
"url": "https://agent-router.org/mcp-http/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agenttoagent-mcp-backend",
"transport": "streamable-http",
"url": "https://agent-router.org/mcp-http/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for agent-router.org was fetched 2026-09-01T19:36:19.802Z.
agent-router.org is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.