Eval runs

Create an eval suite (author-only, does not run)

Creates a runnable eval suite — the suite record plus its test cases — and responds 201 synchronously, WITHOUT executing anything. Use this to author a suite, then run it later with POST /eval-runs (passing the returned suiteId).

This is distinct from POST /eval-runs, which creates a run and detaches execution, responding 202 with a runId. There is no concurrency cap here (no run is started).

The body uses an ergonomic authoring shape: a suite-level default model (and optional provider) applies to every test unless the test overrides it; provider is derived from a provider/model id when neither is supplied. Each test’s case body is an ordered steps array (prompt / toolCall / interact / assert).

Guest callers are denied (suite creation is a write).

POST

projects

{projectId}

eval-suites

Create an eval suite (author-only, does not run)

curl --request POST \
  --url https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "smoke",
  "serverIds": [
    "srv_abc123"
  ],
  "model": "anthropic/claude-haiku-4.5",
  "tests": [
    {
      "title": "lists files",
      "steps": [
        {
          "id": "s1",
          "kind": "prompt",
          "prompt": "List the files in the project root."
        },
        {
          "id": "s2",
          "kind": "assert",
          "assertion": {
            "type": "toolCalledWith",
            "toolName": "list_files",
            "args": {
              "args": {}
            }
          }
        }
      ]
    }
  ]
}
'

import requests

url = "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites"

payload = {
    "name": "smoke",
    "serverIds": ["srv_abc123"],
    "model": "anthropic/claude-haiku-4.5",
    "tests": [
        {
            "title": "lists files",
            "steps": [
                {
                    "id": "s1",
                    "kind": "prompt",
                    "prompt": "List the files in the project root."
                },
                {
                    "id": "s2",
                    "kind": "assert",
                    "assertion": {
                        "type": "toolCalledWith",
                        "toolName": "list_files",
                        "args": { "args": {} }
                    }
                }
            ]
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'smoke',
    serverIds: ['srv_abc123'],
    model: 'anthropic/claude-haiku-4.5',
    tests: [
      {
        title: 'lists files',
        steps: [
          {id: 's1', kind: 'prompt', prompt: 'List the files in the project root.'},
          {
            id: 's2',
            kind: 'assert',
            assertion: {type: 'toolCalledWith', toolName: 'list_files', args: {args: {}}}
          }
        ]
      }
    ]
  })
};

fetch('https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => 'smoke',
    'serverIds' => [
        'srv_abc123'
    ],
    'model' => 'anthropic/claude-haiku-4.5',
    'tests' => [
        [
                'title' => 'lists files',
                'steps' => [
                                [
                                                                'id' => 's1',
                                                                'kind' => 'prompt',
                                                                'prompt' => 'List the files in the project root.'
                                ],
                                [
                                                                'id' => 's2',
                                                                'kind' => 'assert',
                                                                'assertion' => [
                                                                                                                                'type' => 'toolCalledWith',
                                                                                                                                'toolName' => 'list_files',
                                                                                                                                'args' => [
                                                                                                                                                                                                                                                                'args' => [
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                
                                                                                                                                                                                                                                                                ]
                                                                                                                                ]
                                                                ]
                                ]
                ]
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites"

	payload := strings.NewReader("{\n  \"name\": \"smoke\",\n  \"serverIds\": [\n    \"srv_abc123\"\n  ],\n  \"model\": \"anthropic/claude-haiku-4.5\",\n  \"tests\": [\n    {\n      \"title\": \"lists files\",\n      \"steps\": [\n        {\n          \"id\": \"s1\",\n          \"kind\": \"prompt\",\n          \"prompt\": \"List the files in the project root.\"\n        },\n        {\n          \"id\": \"s2\",\n          \"kind\": \"assert\",\n          \"assertion\": {\n            \"type\": \"toolCalledWith\",\n            \"toolName\": \"list_files\",\n            \"args\": {\n              \"args\": {}\n            }\n          }\n        }\n      ]\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"smoke\",\n  \"serverIds\": [\n    \"srv_abc123\"\n  ],\n  \"model\": \"anthropic/claude-haiku-4.5\",\n  \"tests\": [\n    {\n      \"title\": \"lists files\",\n      \"steps\": [\n        {\n          \"id\": \"s1\",\n          \"kind\": \"prompt\",\n          \"prompt\": \"List the files in the project root.\"\n        },\n        {\n          \"id\": \"s2\",\n          \"kind\": \"assert\",\n          \"assertion\": {\n            \"type\": \"toolCalledWith\",\n            \"toolName\": \"list_files\",\n            \"args\": {\n              \"args\": {}\n            }\n          }\n        }\n      ]\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"smoke\",\n  \"serverIds\": [\n    \"srv_abc123\"\n  ],\n  \"model\": \"anthropic/claude-haiku-4.5\",\n  \"tests\": [\n    {\n      \"title\": \"lists files\",\n      \"steps\": [\n        {\n          \"id\": \"s1\",\n          \"kind\": \"prompt\",\n          \"prompt\": \"List the files in the project root.\"\n        },\n        {\n          \"id\": \"s2\",\n          \"kind\": \"assert\",\n          \"assertion\": {\n            \"type\": \"toolCalledWith\",\n            \"toolName\": \"list_files\",\n            \"args\": {\n              \"args\": {}\n            }\n          }\n        }\n      ]\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "suiteId": "<string>",
  "name": "<string>",
  "caseUpsert": {
    "committed": [
      {
        "id": "<string>",
        "name": "<string>"
      }
    ],
    "failed": [
      {
        "id": "<string>",
        "name": "<string>",
        "error": "<string>"
      }
    ]
  },
  "servers": [
    {
      "id": "<string>",
      "name": "<string>"
    }
  ],
  "hosts": [
    {
      "id": "<string>",
      "name": "<string>"
    }
  ]
}

Authorizations

Authorization

string

header

required

MCPJam API key (sk_…). Create one at Settings → API keys. Guest sessions cannot use the API, and API keys cannot manage other API keys.

Headers

x-mcpjam-eval-vocabulary

enum<string>

Which vocabulary this request and its response speak. Absent means 1, which is byte-for-byte today's contract: the same request fields, the same refusals, the same response projection. 2 is the canonical vocabulary. Any other value is a 400 with code: "VALIDATION_ERROR".

Today it decides one thing: the spelling of an evaluator's policy role. Vocabulary 1 accepts and returns gating; vocabulary 2 accepts both spellings and returns the canonical required. Sending required without the header is a 400, deliberately — vocabulary 1 is not widened to meet vocabulary 2 half way, because a boundary that accepts a spelling it does not announce is one two implementations can disagree about.

A response that varies by vocabulary sends Vary: x-mcpjam-eval-vocabulary.

Available options:

1,

2

Path Parameters

projectId

string

required

ID of the hosted project that contains the server.

Body

application/json

Author-only suite-create body. A suite-level default model (and optional provider) applies to every test unless the test overrides it.

name

string

required

Suite name.

Minimum string length: 1

serverIds

string[]

required

Servers (by canonical project ID) the suite's cases run against.

Minimum array length: 1

model

string

required

Suite-level default model id (e.g. anthropic/claude-haiku-4.5). Used for any test that omits model.

Minimum string length: 1

tests

object[]

required

Test cases to create in the suite. The object is CLOSED: an unknown key is a VALIDATION_ERROR, never a silently dropped field. repetitions, passThreshold and kind are per-case policy fields this surface cannot author — set them through POST /v1/projects/{projectId}/eval-suites/{suiteId}/cases.

Required array length: 1 - 100 elements

Show child attributes

description

string

serverNames

string[]

Optional display names, parallel to serverIds.

hosts

object[]

Clients (hosts) to attach the suite to, in attach order. A suite with no attached client reports none wherever it is listed, and a run has no host to select. Same shape as the PATCH hosts field.

Show child attributes

provider

string

Optional suite-level default provider. When omitted, the provider is derived from a provider/model id.

passCriteria

object

The floor a run must clear, as a PERCENT in [0, 100] — 80 means 80%. minimumPassRatePercent is the canonical spelling (the unit is in the name); minimumPassRate is the deprecated alias for it. Send exactly one. THE NAME DISAMBIGUATES THE UNIT: a value in (0, 1) is accepted on minimumPassRatePercent, where it unambiguously means a sub-1% floor the evaluator can act on, and REJECTED on the bare minimumPassRate, where 0.8 cannot be told apart from a fraction sent by mistake and would silently make the gate unfailable. Neither field ever reinterprets a value. A per-case passThreshold IS a fraction; this suite/run floor is not.

Option 1
Option 2

Show child attributes

Response

The suite was created.

suiteId

string

required

name

string

required

caseUpsert

object

required

Per-case create outcomes. Partial failures don't abort the suite; an all-failed new suite is rejected with VALIDATION_ERROR.

Show child attributes

servers

object[]

The servers attached to the suite. name is present when supplied.

Show child attributes

hosts

object[]

The clients (hosts) attached to the suite at create time. Empty when none were named.

Show child attributes

⌘I

Create an eval suite (author-only, does not run)

curl --request POST \
  --url https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "smoke",
  "serverIds": [
    "srv_abc123"
  ],
  "model": "anthropic/claude-haiku-4.5",
  "tests": [
    {
      "title": "lists files",
      "steps": [
        {
          "id": "s1",
          "kind": "prompt",
          "prompt": "List the files in the project root."
        },
        {
          "id": "s2",
          "kind": "assert",
          "assertion": {
            "type": "toolCalledWith",
            "toolName": "list_files",
            "args": {
              "args": {}
            }
          }
        }
      ]
    }
  ]
}
'

import requests

url = "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites"

payload = {
    "name": "smoke",
    "serverIds": ["srv_abc123"],
    "model": "anthropic/claude-haiku-4.5",
    "tests": [
        {
            "title": "lists files",
            "steps": [
                {
                    "id": "s1",
                    "kind": "prompt",
                    "prompt": "List the files in the project root."
                },
                {
                    "id": "s2",
                    "kind": "assert",
                    "assertion": {
                        "type": "toolCalledWith",
                        "toolName": "list_files",
                        "args": { "args": {} }
                    }
                }
            ]
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'smoke',
    serverIds: ['srv_abc123'],
    model: 'anthropic/claude-haiku-4.5',
    tests: [
      {
        title: 'lists files',
        steps: [
          {id: 's1', kind: 'prompt', prompt: 'List the files in the project root.'},
          {
            id: 's2',
            kind: 'assert',
            assertion: {type: 'toolCalledWith', toolName: 'list_files', args: {args: {}}}
          }
        ]
      }
    ]
  })
};

fetch('https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => 'smoke',
    'serverIds' => [
        'srv_abc123'
    ],
    'model' => 'anthropic/claude-haiku-4.5',
    'tests' => [
        [
                'title' => 'lists files',
                'steps' => [
                                [
                                                                'id' => 's1',
                                                                'kind' => 'prompt',
                                                                'prompt' => 'List the files in the project root.'
                                ],
                                [
                                                                'id' => 's2',
                                                                'kind' => 'assert',
                                                                'assertion' => [
                                                                                                                                'type' => 'toolCalledWith',
                                                                                                                                'toolName' => 'list_files',
                                                                                                                                'args' => [
                                                                                                                                                                                                                                                                'args' => [
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                
                                                                                                                                                                                                                                                                ]
                                                                                                                                ]
                                                                ]
                                ]
                ]
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites"

	payload := strings.NewReader("{\n  \"name\": \"smoke\",\n  \"serverIds\": [\n    \"srv_abc123\"\n  ],\n  \"model\": \"anthropic/claude-haiku-4.5\",\n  \"tests\": [\n    {\n      \"title\": \"lists files\",\n      \"steps\": [\n        {\n          \"id\": \"s1\",\n          \"kind\": \"prompt\",\n          \"prompt\": \"List the files in the project root.\"\n        },\n        {\n          \"id\": \"s2\",\n          \"kind\": \"assert\",\n          \"assertion\": {\n            \"type\": \"toolCalledWith\",\n            \"toolName\": \"list_files\",\n            \"args\": {\n              \"args\": {}\n            }\n          }\n        }\n      ]\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"smoke\",\n  \"serverIds\": [\n    \"srv_abc123\"\n  ],\n  \"model\": \"anthropic/claude-haiku-4.5\",\n  \"tests\": [\n    {\n      \"title\": \"lists files\",\n      \"steps\": [\n        {\n          \"id\": \"s1\",\n          \"kind\": \"prompt\",\n          \"prompt\": \"List the files in the project root.\"\n        },\n        {\n          \"id\": \"s2\",\n          \"kind\": \"assert\",\n          \"assertion\": {\n            \"type\": \"toolCalledWith\",\n            \"toolName\": \"list_files\",\n            \"args\": {\n              \"args\": {}\n            }\n          }\n        }\n      ]\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-suites")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"smoke\",\n  \"serverIds\": [\n    \"srv_abc123\"\n  ],\n  \"model\": \"anthropic/claude-haiku-4.5\",\n  \"tests\": [\n    {\n      \"title\": \"lists files\",\n      \"steps\": [\n        {\n          \"id\": \"s1\",\n          \"kind\": \"prompt\",\n          \"prompt\": \"List the files in the project root.\"\n        },\n        {\n          \"id\": \"s2\",\n          \"kind\": \"assert\",\n          \"assertion\": {\n            \"type\": \"toolCalledWith\",\n            \"toolName\": \"list_files\",\n            \"args\": {\n              \"args\": {}\n            }\n          }\n        }\n      ]\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "suiteId": "<string>",
  "name": "<string>",
  "caseUpsert": {
    "committed": [
      {
        "id": "<string>",
        "name": "<string>"
      }
    ],
    "failed": [
      {
        "id": "<string>",
        "name": "<string>",
        "error": "<string>"
      }
    ]
  },
  "servers": [
    {
      "id": "<string>",
      "name": "<string>"
    }
  ],
  "hosts": [
    {
      "id": "<string>",
      "name": "<string>"
    }
  ]
}

API Guides

Endpoints

Create an eval suite (author-only, does not run)

Authorizations

Headers

Path Parameters

Body

Response