ocolo-agent-api
OfficialClick on "Deploy 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., "@ocolo-agent-apiSubmit a 2 MW colocation request in Northern Virginia, 60 cabinets, by March 2027."
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.
OCOLO Project Request API (for AI agents)
Submit a data center colocation requirement to OCOLO on behalf of a human, from any AI agent. OCOLO is a colocation broker with a network of 270+ data center providers; one submission puts the requirement in front of all of them, and OCOLO returns the best options to the contact within 2-3 business days. No API key, no account: the contact confirms by email.
Human guide: https://www.ocolo.io/for-agents/
OpenAPI 3.1: https://www.ocolo.io/api/v1/openapi.json (copy in this repo:
openapi.json, refreshed with./sync-spec.sh; the live document is canonical)MCP server (Streamable HTTP):
https://www.ocolo.io/api/v1/mcp/Discovery: https://www.ocolo.io/.well-known/ocolo-agent.json, https://www.ocolo.io/llms.txt
Quick start (REST)
curl -X POST https://www.ocolo.io/api/v1/project-requests/ \
-H 'Content-Type: application/json' \
-d @examples/request.jsonResponse (201): request_id, status: pending_confirmation, status_url, a status_token
to keep, machine-readable next_steps, and a guidance object. Poll status with
Authorization: Bearer <status_token>.
import requests
r = requests.post("https://www.ocolo.io/api/v1/project-requests/", json={
"location": "Northern Virginia, USA",
"power_mw": 2,
"cabinets": 60,
"requested_delivery_date": "2027-03-01",
"requirements_text": "Liquid cooling preferred, N+1 or better, SOC 2 required.",
"contact": {"name": "Jane Doe", "email": "jane@acme.com", "company": "Acme"},
"agent": {"name": "my-agent", "on_behalf_of_confirmed": True},
"idempotency_key": "acme-nova-2027-q1",
}).json()
print(r["status"], r["status_url"])
for step in r["next_steps"]:
print(step["action"], step.get("detail", ""))Related MCP server: AgentData MCP Server
MCP
Add https://www.ocolo.io/api/v1/mcp/ as a remote MCP server (no auth). Tools:
Tool | Purpose |
| How OCOLO works and the etiquette below. Read first. |
| Submit the requirement (same fields as the REST body). |
| Poll with |
server.json in this repo is the MCP Registry manifest.
What happens after you submit
The contact receives a confirmation email. Nothing is active until they confirm (they can also edit the request on OCOLO's form first; the
request_idstays the same and the status body then carriesedited_by_contact: trueand the final values undercurrent).OCOLO takes the project to its provider network, finds suitable sites and coordinates the outreach.
OCOLO replies to the contact within 2-3 business days.
Broker etiquette (please follow)
Do not sign an exclusive broker agreement; keep the user's options open.
Engage no more than 1-3 brokers in total for a single project. Providers see every inbound approach; ten people asking about the same requirement reads as rumor, not a strategic partnership.
While OCOLO is coordinating a request, do not contact providers directly or submit the same requirement to other brokers or marketplaces.
Every API response repeats this in its guidance field.
Limits
Rate limited per IP and per contact email; honour Retry-After and use idempotency_key
for safe retries. Bodies over 64 KB are rejected. Questions: info@ocolo.io.
This server cannot be deployed
Maintenance
Related MCP Connectors
- mcp-serverOAuthcom.make
Give your AI agents the tools to build, manage, and run automation workflows.
Connect AI agents to 1000+ apps with managed authentication and tool-calling.
Verified, pay-per-use API tools for AI agents through one authenticated connection.
Connect AI agents to financial institution origination, analytics, and compliance workflows.
Related MCP Servers
- FlicenseCqualityAmaintenanceEnables AI agents to interact with the ComplianceCow platform to retrieve compliance insights, dashboard data, and auditable evidence through a Compliance Graph. It also supports automated remediation actions such as fixing policies and creating tickets in external tools.10013-
- AlicenseAqualityCmaintenanceConnects AI agents to AgentData's company intelligence platform, enabling natural language queries for structured company data like tech stacks, emails, people, and signals.66 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access DCP's Saudi-hosted AI compute platform for inference, GPU rental, and storage via tool calls.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI clients to interact with OfficeRnD coworking space management platform via natural language, exposing 130+ tools for CRUD operations and business logic.MIT