Eval runs
List run iterations
Per-iteration results: actual tool calls, structured token usage, and latency. Cursor-paginated.
GET
/
projects
/
{projectId}
/
eval-runs
/
{runId}
/
iterations
List run iterations
curl --request GET \
--url https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations \
--header 'Authorization: Bearer <token>'import requests
url = "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations', 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-runs/{runId}/iterations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"items": [
{
"id": "<string>",
"iterationNumber": 123,
"status": "pending",
"actualToolCalls": [
{}
],
"expectedToolCalls": [
{}
],
"testCaseId": "<string>",
"caseId": "<string>",
"title": "<string>",
"result": "passed",
"model": "<string>",
"provider": "<string>",
"startedAt": 123,
"durationMs": 123,
"tokensUsed": 123,
"usage": {},
"error": "<string>",
"scores": [
{
"scorerId": "<string>",
"scorerVersion": "<string>",
"definitionHash": "<string>",
"status": "scored",
"passThreshold": 0.5,
"deterministic": true,
"value": 0.5,
"passed": true,
"rationale": "<string>",
"evidence": [
"<string>"
],
"model": "<string>",
"promptHash": "<string>",
"error": "<string>",
"scope": {}
}
],
"evaluationConfig": {
"hash": "<string>",
"definitions": [
{
"scorerId": "<string>",
"idSource": "explicit",
"scorerVersion": "<string>",
"implementationHash": "<string>",
"deterministic": true,
"passThreshold": 0.5,
"role": "gating",
"onError": "fail",
"onSkipped": "fail",
"label": "<string>",
"model": "<string>",
"scope": {}
}
]
},
"scoreIntegrity": "score_integrity_invalid",
"stageResults": [
{
"stage": "connection",
"state": "passed",
"reason": "noSpanChannel",
"evidence": {
"spanIds": [
"<string>"
],
"promptIndexes": [
123
],
"predicateReasons": [
"<string>"
]
}
}
],
"firstFailedStage": "connection",
"failureCategory": "setup",
"stageAnalyzerVersion": 1,
"stageResultsUnverified": true,
"frictionSignals": {
"version": 1,
"state": "measured",
"callCount": 1,
"resultAvailableCount": 1,
"timedCallCount": 1,
"identifierSignals": {
"state": "measured",
"reason": "noToolCalls"
},
"signals": [
{
"kind": "identifierSurfacedUnused",
"toolName": "<string>",
"toolCallId": "<string>",
"informationCallIndex": 1,
"observedAtCallIndex": 1,
"callIndex": 1,
"priorCallIndex": 1,
"afterError": true,
"identifierKeyPaths": [
"<string>"
],
"identifierCount": 2,
"laterCallCount": 3,
"repeatCallIndexes": [
1
],
"paginationKeys": [
"cursor"
]
}
],
"notMeasuredReason": "noToolCalls"
},
"frictionSignalsUnverified": true,
"suspectedConditionVerdict": {
"status": "scored",
"gradingKey": "<string>",
"signalKind": "<string>",
"informationCallIndex": 1,
"observedAtCallIndex": 1,
"judgeTemplateVersion": 2,
"judgeTemplateHash": "<string>",
"model": "<string>",
"generatedAt": 1,
"reason": "spendBlocked",
"condition": "unclear",
"confidence": "low",
"remediation": "<string>",
"evidence": {
"callIndex": 1,
"toolName": "<string>",
"fieldPath": "<string>"
}
},
"suspectedConditionUnverified": true
}
],
"nextCursor": "<string>"
}
Authorizations
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
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
ID of the hosted project that contains the server.
Eval run ID, as returned by POST /eval-runs.
Query Parameters
Page size, 1–200. Defaults to 50.
Required range:
1 <= x <= 200Opaque cursor from a previous response's nextCursor.
Was this page helpful?
⌘I
List run iterations
curl --request GET \
--url https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations \
--header 'Authorization: Bearer <token>'import requests
url = "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations', 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-runs/{runId}/iterations",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.mcpjam.com/api/v1/projects/{projectId}/eval-runs/{runId}/iterations")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"items": [
{
"id": "<string>",
"iterationNumber": 123,
"status": "pending",
"actualToolCalls": [
{}
],
"expectedToolCalls": [
{}
],
"testCaseId": "<string>",
"caseId": "<string>",
"title": "<string>",
"result": "passed",
"model": "<string>",
"provider": "<string>",
"startedAt": 123,
"durationMs": 123,
"tokensUsed": 123,
"usage": {},
"error": "<string>",
"scores": [
{
"scorerId": "<string>",
"scorerVersion": "<string>",
"definitionHash": "<string>",
"status": "scored",
"passThreshold": 0.5,
"deterministic": true,
"value": 0.5,
"passed": true,
"rationale": "<string>",
"evidence": [
"<string>"
],
"model": "<string>",
"promptHash": "<string>",
"error": "<string>",
"scope": {}
}
],
"evaluationConfig": {
"hash": "<string>",
"definitions": [
{
"scorerId": "<string>",
"idSource": "explicit",
"scorerVersion": "<string>",
"implementationHash": "<string>",
"deterministic": true,
"passThreshold": 0.5,
"role": "gating",
"onError": "fail",
"onSkipped": "fail",
"label": "<string>",
"model": "<string>",
"scope": {}
}
]
},
"scoreIntegrity": "score_integrity_invalid",
"stageResults": [
{
"stage": "connection",
"state": "passed",
"reason": "noSpanChannel",
"evidence": {
"spanIds": [
"<string>"
],
"promptIndexes": [
123
],
"predicateReasons": [
"<string>"
]
}
}
],
"firstFailedStage": "connection",
"failureCategory": "setup",
"stageAnalyzerVersion": 1,
"stageResultsUnverified": true,
"frictionSignals": {
"version": 1,
"state": "measured",
"callCount": 1,
"resultAvailableCount": 1,
"timedCallCount": 1,
"identifierSignals": {
"state": "measured",
"reason": "noToolCalls"
},
"signals": [
{
"kind": "identifierSurfacedUnused",
"toolName": "<string>",
"toolCallId": "<string>",
"informationCallIndex": 1,
"observedAtCallIndex": 1,
"callIndex": 1,
"priorCallIndex": 1,
"afterError": true,
"identifierKeyPaths": [
"<string>"
],
"identifierCount": 2,
"laterCallCount": 3,
"repeatCallIndexes": [
1
],
"paginationKeys": [
"cursor"
]
}
],
"notMeasuredReason": "noToolCalls"
},
"frictionSignalsUnverified": true,
"suspectedConditionVerdict": {
"status": "scored",
"gradingKey": "<string>",
"signalKind": "<string>",
"informationCallIndex": 1,
"observedAtCallIndex": 1,
"judgeTemplateVersion": 2,
"judgeTemplateHash": "<string>",
"model": "<string>",
"generatedAt": 1,
"reason": "spendBlocked",
"condition": "unclear",
"confidence": "low",
"remediation": "<string>",
"evidence": {
"callIndex": 1,
"toolName": "<string>",
"fieldPath": "<string>"
}
},
"suspectedConditionUnverified": true
}
],
"nextCursor": "<string>"
}