
Two MCP tools instead of an API catalog: search endpoints, run Python in a sandbox.
Public tool metadata for what this MCP can expose to an agent.
searchFinds the right endpoints and memory facts, returns compact signatures.Finds the right endpoints and memory facts, returns compact signatures.
No parameter schema in public metadata yet.
runExecutes model-written Python in a sandbox: api.get(path) + vi.add/find/stats.Executes model-written Python in a sandbox: api.get(path) + vi.add/find/stats.
No parameter schema in public metadata yet.
Sponsors
VIBOCODE_CATALOGPath to catalog.json describing the target service
VIBO_MEM_FILEPath to the ViBo memory base (optional, enables persistent memory)
Two tools instead of an API catalog. An MCP server that keeps the agent's context small and its reach long.
search — finds the right endpoints and memory facts, returns compact signatures
run — executes model-written Python in a sandbox: api.get(path) + vi.add/find/stats
The whole toolset is 217 tokens (o200k_base tokenizer). The same GitHub REST catalog — 1,272 endpoints — costs 79,525 tokens as plain MCP tools: a 366x difference. Slack's 174 endpoints: 42x. Measurements and reproduction commands are in Benchmarks.
npx vibocode-mcp
Requires Node 18+ and Python 3.10+ (the server is Python).
MCP client configuration:
{
"mcpServers": {
"vibocode": {
"command": "npx",
"args": ["-y", "vibocode-mcp"],
"env": {
"VIBOCODE_CATALOG": "/path/to/catalog.json",
"VIBO_MEM_FILE": "/path/to/memory.web"
}
}
}
}
catalog.json describes a service: base URL, allowed domains and the list of actions.
vibocode-mcp