RunAgents MCP Server
Model Context Protocol server for the RunAgents AI agent platform. Gives AI coding assistants (Claude Code, Cursor, Codex) direct access to deploy agents, manage tools, monitor runs, and handle approvals.
Install
pip install runagents-mcp
Configure
Claude Code
Add to your settings.json or project .mcp.json:
{
"mcpServers": {
"runagents": {
"command": "runagents-mcp",
"env": {
"RUNAGENTS_ENDPOINT": "https://YOUR_WORKSPACE.try.runagents.io",
"RUNAGENTS_API_KEY": "YOUR_API_KEY",
"RUNAGENTS_NAMESPACE": "default"
}
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"runagents": {
"command": "runagents-mcp",
"env": {
"RUNAGENTS_ENDPOINT": "https://YOUR_WORKSPACE.try.runagents.io",
"RUNAGENTS_API_KEY": "YOUR_API_KEY",
"RUNAGENTS_NAMESPACE": "default"
}
}
}
}
Configuration
The server reads configuration from environment variables, falling back to ~/.runagents/config.json (shared with the RunAgents CLI):
| Variable | Description | Default |
|---|---|---|
RUNAGENTS_ENDPOINT |
Platform API URL | http://localhost:8092 |
RUNAGENTS_API_KEY |
API key or workspace key | — |
RUNAGENTS_NAMESPACE |
Target namespace | default |
Tools
| Tool | Description | Type |
|---|---|---|
list_agents |
List all deployed agents | Read |
get_agent |
Get details for a specific agent | Read |
list_tools |
List registered tools | Read |
list_models |
List model providers | Read |
list_runs |
List agent runs | Read |
get_run_events |
Get events for a specific run | Read |
export_context |
Export full workspace context | Read |
analyze_code |
Analyze source code for tool and LLM usage | Read |
deploy_agent |
Deploy an agent from source code or image | Mutate |
create_tool |
Register a new tool | Mutate |
validate_plan |
Validate an action plan before applying | Read |
apply_plan |
Apply a validated action plan | Mutate |
approve_request |
Approve a pending access request | Mutate |
seed_starter_kit |
Create demo tools and model provider | Mutate |
Documentation
- AI Assistant Setup — Full setup guide
- RunAgents Docs — Platform documentation
- CLI Reference — CLI commands
Metadata
Release files for runagents-mcp 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| runagents_mcp-0.1.0.tar.gz | 4.7 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| runagents_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 10.5 kB
Release files / runagents_mcp-0.1.0.tar.gz
| Download URL | runagents_mcp-0.1.0.tar.gz |
|---|---|
| Size | 4.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
74648a7d6c0deb1744a8da5afedbf63216117acbdfdb7901d9307cb3a437632f
|
|
BLAKE2b-256 checksum How to use checksums |
502228cceaaaf227cdae3423e4c2aaa208f0bc4393ee6d11441d3d8d69bbcd7e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.1
|
Release files / runagents_mcp-0.1.0-py3-none-any.whl
| Download URL | runagents_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d3502816703350c6b9ec7381268ce70b547789ac3a6b57b3e5da3ea2b610bb85
|
|
BLAKE2b-256 checksum How to use checksums |
d523836f007145f61bbd76b3d3bab7baac268456d3ee4fe40c152a6a511e3f37
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.1
|
Security for runagents-mcp 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.