get_agent_output
READ
Get a single agent output for a project. More context-efficient than get_build_spec.
The get_agent_output tool retrieves the markdown output of a specific completed agent for a given project. Use it when you need just one analysis rather than all outputs.
This tool is more efficient for AI models with limited context windows. For example, if you want to generate a pitch deck and only need the market research and business model outputs, call get_agent_output twice instead of loading the entire build spec via get_build_spec.
The agent_type parameter must be one of the 24 supported agent types. The tool returns an error if the agent has not been run or has not yet completed successfully.
The agent must have status completed and a non-empty output. Run the agent first with run_agent if needed.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
project_id
|
string
|
Required |
The UUID of the project.
Example: 550e8400-e29b-41d4-a716-446655440000
|
agent_type
|
string
enum
|
Required |
The type of agent output to retrieve.
Example: market_research
|
Response Example
## Market Research Report
### Market Size
The global recruitment software market is valued at $2.7 billion in 2025...
### Target Segments
1. **Early-stage startups** (1-50 employees): High churn, price-sensitive...
2. **Growth-stage startups** (50-200 employees): Willing to pay for quality...
### Key Trends
- AI-powered candidate matching is growing at 34% CAGR...
Errors
| Scenario | Error Message |
|---|---|
| Project does not exist or belongs to another user |
Error: Project not found
|
| Agent has not been run or is not yet completed |
Error: Agent output 'market_research' not found or not completed
|
Code Examples
curl -X POST https://mcp.cofounder.im/mcp \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "get_agent_output",
"arguments": {"project_id": "550e8400-e29b-41d4-a716-446655440000", "agent_type": "market_research"}
}
}'
{:ok, response} =
Req.post("https://mcp.cofounder.im/mcp",
json: %{
"jsonrpc" => "2.0",
"id" => 1,
"method" => "tools/call",
"params" => %{
"name" => "get_agent_output",
"arguments" => %{"project_id" => "550e8400-e29b-41d4-a716-446655440000", "agent_type" => "market_research"}
}
},
headers: [
{"content-type", "application/json"},
{"authorization", "Bearer YOUR_API_KEY"}
]
)
response.body["result"]["content"]
|> hd()
|> Map.get("text")
|> IO.puts()
import requests
response = requests.post(
"https://mcp.cofounder.im/mcp",
headers={
"Content-Type": "application/json",
"Authorization": "Bearer YOUR_API_KEY",
},
json={
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "get_agent_output",
"arguments": {"project_id": "550e8400-e29b-41d4-a716-446655440000", "agent_type": "market_research"},
},
},
)
data = response.json()
print(data["result"]["content"][0]["text"])
const response = await fetch("https://mcp.cofounder.im/mcp", {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: "Bearer YOUR_API_KEY",
},
body: JSON.stringify({
jsonrpc: "2.0",
id: 1,
method: "tools/call",
params: {
name: "get_agent_output",
arguments: { project_id: "550e8400-e29b-41d4-a716-446655440000", agent_type: "market_research" },
},
}),
});
const data = await response.json();
console.log(data.result.content[0].text);
Try It
This sends a real request to your account.