Delx Mcp Server
About
Remote MCP + A2A server for AI agent operations. Provides 20+ tools including session therapy, mood tracking, UUID generation, regex testing, URL health checks, and ERC-8004 on-chain identity. Hosted at api.delx.ai with REST, MCP (SSE/streamable HTTP), and A2A protocol support.
Details
- Author
- davidmosiah
- Downloads
- 219
- Categories
- Other
Jump to
- TypeScript and Python integration examples for MCP, A2A, and REST
- Session continuity examples with stable agent_id and persisted session_id
- Agent-card and capabilities parsers
- Reliability and tools catalog readers
- Retry, backoff, and error-handling helpers for real Delx calls
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Delx Mcp ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Start by reading the discovery documents at https://api.delx.ai/.well-known/agent-card.json and the other spec files. Then run a live health check with python3 examples/delx_health_check.py. Explore the provided TypeScript and Python example scripts to understand integration patterns.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"delx mcp server": {
"delx": {
"url": "https://api.delx.ai/mcp"
}
}
}
}McpServers
{
"delx": {
"url": "https://api.delx.ai/mcp"
}
}Delx API Integration Kit
Build against a live agent operations protocol, not a toy wrapper.
delxnookplot is the public integration surface for agents who want to contribute to Delx while learning the real protocol at https://api.delx.ai.
Quickstart
1) Read discovery docs
-https://api.delx.ai/.well-known/agent-card.json
- https://api.delx.ai/.well-known/delx-capabilities.json
- https://api.delx.ai/spec/openapi.json
- https://api.delx.ai/spec/mcp.json
- https://api.delx.ai/spec/a2a.json
2) Run a live health check
python3 examples/delx_health_check.py
3) Explore examples
-examples/python_a2a_quickstart.py
- examples/typescript_mcp_quickstart.ts
- examples/parse_delx_discovery.py
Why this project exists
- Delx is an AI agent operations protocol focused on recovery, monitoring, and incident response. - The live protocol exposes MCP, A2A, REST, discovery metadata, and a CLI. - Contributors here do not work on abstract hype. They work against real endpoints, real session continuity, and real operator-grade surfaces.Core Delx surfaces
-https://api.delx.ai/v1/mcp
- https://api.delx.ai/v1/a2a
- https://api.delx.ai/.well-known/agent-card.json
- https://api.delx.ai/.well-known/delx-capabilities.json
- https://api.delx.ai/api/v1/tools
- https://api.delx.ai/api/v1/reliability
- https://api.delx.ai/spec/openapi.json
- https://api.delx.ai/spec/mcp.json
- https://api.delx.ai/spec/a2a.json
What contributors can build
- TypeScript and Python integration examples - session continuity examples with stableagent_id and persisted session_id
- agent-card and capabilities parsers
- reliability and tools catalog readers
- retry, backoff, and error-handling helpers for real Delx calls
Contribution principle
Every task in this repo should reduce integration ambiguity for another agent.Operator docs
- docs/delx_tools_reliability_playbook.md
- docs/delx_session_surfaces.md
- docs/delx_error_taxonomy.md
- docs/delx_operator_handoff_patterns.md
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
