Catalog

Search or list unified sessions

The unified, cross-surface sessions feed for one project: Playground, user-testing, eval, and swarm transcripts in one list, newest first. Project-NESTED (unlike /chat-sessions) because projectId owns the scope here rather than filtering it.

Under x-mcpjam-api-vocabulary: 2 each item’s sourceType reads study where it reads scenario today, and parentRef reads kind: "study" / kind: "goalRun" with its id fields re-keyed to studyId / goalRunId / goalRefId. The sourceType filter accepts either spelling under that header.

Supplying q at all switches to relevance-ordered search; scope then chooses what is searched. Row-level visibility applies in every mode: a caller never receives another member’s private Playground session.

The response echoes the honored scope. A deployment predating that parameter omits the echo — clients requesting a non-default scope MUST treat its absence as “unsupported” rather than accepting the results.

GET

projects

{projectId}

sessions

Search or list unified sessions

curl --request GET \
  --url https://app.mcpjam.com/api/v1/projects/{projectId}/sessions \
  --header 'Authorization: Bearer <token>'

import requests

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

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}/sessions', 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}/sessions",
  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}/sessions"

	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))

}

require 'uri'
require 'net/http'

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

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>",
      "chatSessionId": "<string>",
      "projectId": "<string>",
      "sourceType": "direct",
      "origin": "<string>",
      "status": "<string>",
      "synthetic": true,
      "lockReason": "<string>",
      "title": "<string>",
      "firstMessagePreview": "<string>",
      "visibility": "<string>",
      "ownedByViewer": true,
      "startedAt": 123,
      "lastActivityAt": 123,
      "modelId": "<string>",
      "messageCount": 123,
      "parentRef": {
        "kind": "evalRun",
        "label": "<string>",
        "iterationId": "<string>",
        "suiteRunId": "<string>",
        "suiteId": "<string>",
        "journeyRunId": "<string>",
        "goalRunId": "<string>",
        "journeyRefId": "<string>",
        "goalRefId": "<string>",
        "scenarioId": "<string>",
        "studyId": "<string>"
      },
      "link": {
        "path": "<string>",
        "url": "<string>"
      },
      "cumulativeUserMessageCount": 123,
      "cumulativeToolCallCount": 123,
      "cumulativeInputTokens": 123,
      "cumulativeOutputTokens": 123,
      "matchPreview": "<string>"
    }
  ],
  "nextCursor": "<string>",
  "scope": "titles"
}

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-api-vocabulary

enum<string>

Which spelling of the API's resource-noun VALUES this request and its response speak. Absent means 1, byte-for-byte today's contract. 2 is the canonical vocabulary. Any other value is a 400 with code: "VALIDATION_ERROR".

Three nouns were renamed at this boundary — scenario → study, journey → goal, wave → swarm run. Operation names, routes, type names and field names each moved behind a deprecated alias, because a caller reaches them by a name it chose. A VALUE cannot: sourceType is one field with one string in it, and a client switching on "scenario" has no second name to fall back to. Under vocabulary 2 a session’s sourceType reads study, a share’s resourceType reads study, and a session’s parentRef.kind reads study or goalRun with its id fields re-keyed to match.

On the way IN, a vocabulary-2 request may name a filter or a path segment by EITHER spelling; a vocabulary-1 request may use only the legacy one, 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-api-vocabulary. A SEPARATE header from x-mcpjam-eval-vocabulary, which is eval-scoped by name and moves on its own schedule.

Available options:

1,

2

Path Parameters

projectId

string

required

ID of the hosted project that contains the server.

Query Parameters

string

Search terms. Supplying this at all switches from the recency feed to relevance-ordered search; q= (blank) is an empty search, not "no filter".

scope

enum<string>

default:titles

What to search. titles (default) matches titles and opening messages; transcripts matches conversation content. Requires q; an unknown value is a 400.

Available options:

titles,

transcripts

sourceType

string

Comma-separated surfaces to include: direct, scenario, eval, swarm. Omit for all. An unknown value is a 400 rather than a silent widening.

status

enum<string>

default:active

active (default) or archived.

Available options:

active,

archived

limit

integer

default:50

Page size, 1–200. Defaults to 50.

Required range: 1 <= x <= 200

cursor

string

Opaque cursor: echo back the previous page's nextCursor. Never construct one, and never assume it encodes a timestamp. Cursors do not cross scopes — page with the parameters you opened with.

Response

One page of sessions — newest first when listing, most relevant first when searching.

items

object[]

required

Show child attributes

nextCursor

string

Pass as cursor to fetch the next page. Omitted on the last page.

scope

enum<string>

The scope the server actually honored. ABSENT from deployments predating the parameter — treat its absence as "transcript search unsupported".

Available options:

titles,

transcripts

⌘I

Search or list unified sessions

curl --request GET \
  --url https://app.mcpjam.com/api/v1/projects/{projectId}/sessions \
  --header 'Authorization: Bearer <token>'

import requests

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

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}/sessions', 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}/sessions",
  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}/sessions"

	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))

}

require 'uri'
require 'net/http'

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

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>",
      "chatSessionId": "<string>",
      "projectId": "<string>",
      "sourceType": "direct",
      "origin": "<string>",
      "status": "<string>",
      "synthetic": true,
      "lockReason": "<string>",
      "title": "<string>",
      "firstMessagePreview": "<string>",
      "visibility": "<string>",
      "ownedByViewer": true,
      "startedAt": 123,
      "lastActivityAt": 123,
      "modelId": "<string>",
      "messageCount": 123,
      "parentRef": {
        "kind": "evalRun",
        "label": "<string>",
        "iterationId": "<string>",
        "suiteRunId": "<string>",
        "suiteId": "<string>",
        "journeyRunId": "<string>",
        "goalRunId": "<string>",
        "journeyRefId": "<string>",
        "goalRefId": "<string>",
        "scenarioId": "<string>",
        "studyId": "<string>"
      },
      "link": {
        "path": "<string>",
        "url": "<string>"
      },
      "cumulativeUserMessageCount": 123,
      "cumulativeToolCallCount": 123,
      "cumulativeInputTokens": 123,
      "cumulativeOutputTokens": 123,
      "matchPreview": "<string>"
    }
  ],
  "nextCursor": "<string>",
  "scope": "titles"
}

API Guides

Endpoints

Search or list unified sessions

Authorizations

Headers

Path Parameters

Query Parameters

Response