# How to connect Past.dev with ChatGPT

```json
{
  "title": "How to connect Past.dev with ChatGPT",
  "toolkit": "Past.dev",
  "toolkit_slug": "past_dev",
  "framework": "ChatGPT",
  "framework_slug": "chatgpt",
  "url": "https://composio.dev/toolkits/past_dev/framework/chatgpt",
  "markdown_url": "https://composio.dev/toolkits/past_dev/framework/chatgpt.md",
  "updated_at": "2026-11-06T05:31:17.889Z"
}
```

## Introduction

### How to connect Past.dev MCP with ChatGPT
[ChatGPT](https://chatgpt.com/) can take action across your apps and files, stay with a project for hours, and turn a goal into finished materials like sheets, slides, and docs, not just answers.
In this guide, I will explain the easiest and most secure way to connect your Past.dev account to ChatGPT via Composio Connect, so it can store memories, recall source-backed context, inspect memory traces, manage identities, and clean up data through natural language commands without ever putting your account credentials at risk.

## Also integrate Past.dev with

- [Claude Cowork](https://composio.dev/toolkits/past_dev/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/past_dev/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/past_dev/framework/atomic-agent)

## TL;DR

### Why use Composio over default connectors?
- Apps with read and write access. Default connectors mostly can read your data. Composio's Past.dev integration lets ChatGPT take actions like creating drafts, sending updates, labeling records, and more.
- 1,500+ SaaS toolkits out of the box. Composio gives you instant access to a vast catalog of pre-built connectors, from Gmail and Slack to Notion, Linear, and Salesforce.
- One MCP server for every app. Connect any of your applications on demand through a single endpoint, rather than juggling a separate server for each app.
- Smart, context-aware tool loading. Unlike traditional MCP servers that dump every available tool into the LLM context window, Composio searches for and loads only the tools relevant to the task at hand.
- Cross-app automation. Chain actions across multiple apps in a single run - fetch a thread, summarize it in Notion, and post highlights to Slack without leaving the conversation.

## Connect Past.dev to ChatGPT

### Prerequisites
- A ChatGPT account. We will use the [ChatGPT desktop app](https://openai.com/chatgpt/download/), and the steps are the same on the web.
- Access to the Past.dev workspace you want to connect.
- [Composio plugin](https://dashboard.composio.dev/login?utm_source=toolkits&utm_medium=framework_template&utm_campaign=chatgpt&utm_content=composio_connect&next=%2F~%2Forg%2Fconnect%2Fclients%2Fchatgpt).
Note: Composio connects through OAuth. You will be asked to sign in and approve specific permissions. Review the permission screen carefully if you are using a work account.
### Step-by-step: Connect Past.dev to ChatGPT
### 1. Install the Composio plugin
Click the button. ChatGPT opens the Composio plugin page. Click Install plugin.
[Install in ChatGPT](https://chatgpt.com/plugins/plugin_asdk_app_6a58503580c08191b78cc5bdaf4eba6e)
You can also find it inside ChatGPT: go to Settings, open Plugins, search the marketplace for Composio, and click Install plugin.
### 2. Authenticate
After you install, ChatGPT asks you to authenticate with Composio. Log in and click Allow access to authorize ChatGPT to use your Composio account.
### 3. Start using Composio
That is it. Composio tools are now available in ChatGPT. Type @Composio followed by your request, for example @Composio find unread Past.dev messages and summarize them, and it will run the actions you authorize. On first use it asks you to authorize Past.dev.
### Option 2: Add Composio as an MCP server
If you cannot use the plugin marketplace, add Composio as a custom MCP server instead.
### 1. Open the MCP settings
In ChatGPT, go to Settings and open the Plugins section. Inside the Plugins page, click the MCP tab.
### 2. Add the server
Click Add server. In the Name field enter Composio, for Type select Streamable HTTP, and in the URL field paste the Composio MCP server URL:

```bash
https://connect.composio.dev/mcp
```

## What is the Past.dev MCP server, and what's possible with it?

The Past.dev MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Past.dev account. It provides structured and secure access to durable, source-backed memory, identities, audiences, usage data, diagnostics, and request history, so your agent can store and recall memories, manage identity access, diagnose ingestion, and inspect or clean up memory on your behalf.
- Durable memory ingestion and recall: Have your agent store timestamped information, ingest memory in batches, and recall ranked, source-backed context for an identity.
- Identity and audience management: Let the agent create, update, list, or remove identities and organize access with fixed or trait-based audiences.
- Ingestion diagnostics: Direct your agent to estimate ingestion costs, check processing status, explain partial or failed ingestions, and retry eligible work.
- Usage and activity monitoring: Instruct your agent to review credit usage, inspect API request history, and analyze request counts over selected time periods.
- Memory lineage and cleanup: Have your agent trace how memories and source information relate over time, inspect timeline details, and permanently delete selected memory data when needed.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `PAST_DEV_BULK_REPLACE_IDENTITIES` | Replace Identities in Bulk | Atomically create or replace complete trait sets for up to 1,000 identities; omitted traits replace the identity with no traits. |
| `PAST_DEV_DELETE_AUDIENCE` | Delete Audience | DESTRUCTIVE ACCESS CHANGE: Permanently delete an audience. Its stored memory remains but becomes permanently unreachable. The default project audience cannot be deleted. |
| `PAST_DEV_DELETE_IDENTITY` | Delete Identity | DESTRUCTIVE: Permanently delete an identity directory record and remove it from every audience. Stored memory associated with the identity remains and is not deleted. |
| `PAST_DEV_DELETE_INGESTION_MEMORY` | Permanently Delete Ingestion Memory | DESTRUCTIVE: Permanently delete every data point accepted by one ingestion and memory depending only on those points. This cannot be undone; the ingestion status and audit record remains readable. |
| `PAST_DEV_DELETE_MEMORY_DATA_POINT` | Delete Memory Data Point | DESTRUCTIVE: Permanently delete one data point by its caller-owned source id and remove memory derived from it. This cannot be undone; the purge completes asynchronously. |
| `PAST_DEV_DELETE_MEMORY_DATA_POINTS` | Delete Memory Data Points | DESTRUCTIVE: Permanently and atomically delete up to 1,000 data points by caller-owned source id and remove memory derived from them. This cannot be undone; the purge completes asynchronously. |
| `PAST_DEV_ESTIMATE_INGESTION` | Estimate Ingestion | Cut files into data points, plan batches, and estimate credits without storing data or spending credits. |
| `PAST_DEV_EXPLAIN_INGESTION` | Explain Ingestion | Diagnose how far one send progressed, including per-item searchability, memory counts, failure details, and the recommended next step. |
| `PAST_DEV_FIND_TRACE_ROOTS` | Find Trace Roots | Find memory and source nodes for lineage or timeline inspection, returning independent memory and source cursors. |
| `PAST_DEV_GET_AUDIENCE` | Get Audience | Read one fixed, rule, or default audience with its definition and current membership and memory counts. |
| `PAST_DEV_GET_IDENTITY` | Get Identity | Return one identity's traits, origin, timestamps, and current audience memberships. |
| `PAST_DEV_GET_INGESTION_STATUS` | Get Ingestion Status | Poll one ingestion for processing, completion, failure, and project readiness without consuming metered request quota. |
| `PAST_DEV_GET_REQUEST` | Get API Request | Read one API call and its retained allowlisted headers and request/response payload; bearer credentials are never returned. |
| `PAST_DEV_GET_REQUEST_HISTOGRAM` | Get Request Histogram | Count accepted, failed-later, and rejected API calls in provider-selected time buckets using request-log filters. |
| `PAST_DEV_GET_TRACE_LINEAGE` | Get Trace Lineage | Read what a memory or source was built from and what was built on it, including graph edges and hidden-node count. |
| `PAST_DEV_GET_TRACE_NODE` | Get Trace Node | Read one memory or source node with revision, validity, replacement, request, content, and graph counts. |
| `PAST_DEV_GET_TRACE_TIMELINE` | Get Trace Timeline | Read rooted source and memory work, ingestions, recalls, and supersessions on a clock for a window of at most 31 days. |
| `PAST_DEV_GET_USAGE` | Get Usage | Return the current UTC month's credit balance, metering state, and project ingestion, recall, and cap usage. |
| `PAST_DEV_INGEST_MEMORY` | Ingest Memory | Ingest one timestamped data point into durable memory, optionally associating it with an identity and audience; reusing an id replaces the prior revision when stored fields change. |
| `PAST_DEV_INGEST_MEMORY_BATCH` | Ingest Memory Batch | Atomically ingest 1 to 1,000 ordered memory data points in one request, avoiding fragile per-item agent loops. |
| `PAST_DEV_LIST_AUDIENCES` | List Audiences | List every audience in the connected project, including the default project audience and current membership and memory counts. |
| `PAST_DEV_LIST_IDENTITIES` | List Identities | List project identities newest first, optionally filtering by one trait, and return a cursor for the next page. |
| `PAST_DEV_LIST_REQUESTS` | List API Requests | List the connected project's API calls newest first, with filters and a cursor for the next page. |
| `PAST_DEV_RECALL_MEMORY` | Recall Memory | Return ranked, source-backed memory visible to an identity for a query, with optional time range, sort order, and evidence budget controls. |
| `PAST_DEV_RECOMPUTE_AUDIENCE` | Recompute Audience | Recompute an audience's membership from its definition and apply the refreshed access set to recall immediately. |
| `PAST_DEV_REPLACE_AUDIENCE` | Create or Replace Audience | Create or completely replace a fixed-list or trait-rule audience and its access definition. The default project audience cannot be replaced. |
| `PAST_DEV_REPLACE_IDENTITY` | Replace Identity | Create an identity or replace its complete trait set; omitted or empty traits remove all existing traits. |
| `PAST_DEV_RETRY_INGESTION` | Retry Ingestion | Retry a stopped or failed ingestion under its existing id without spending additional credits; completed ingestions are rejected. |
| `PAST_DEV_UPDATE_IDENTITY_TRAITS` | Update Identity Traits | Merge selected identity traits while preserving unspecified keys; set a trait value to null to remove that key. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

Once connected, ChatGPT can access the Past.dev MCP server via Composio to run actions that you authorize, directly in your workspace.

## Complete Code

None listed.

## How to build Past.dev MCP Agent with another framework

- [Claude Cowork](https://composio.dev/toolkits/past_dev/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/past_dev/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/past_dev/framework/atomic-agent)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [AltTextLab](https://composio.dev/toolkits/alt_text_lab) - AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apiframe](https://composio.dev/toolkits/apiframe) - Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Arize AX](https://composio.dev/toolkits/arize_ax) - Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.
- [Artificial Analysis](https://composio.dev/toolkits/artificial_analysis) - Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings.
- [AssemblyAI](https://composio.dev/toolkits/assemblyai) - AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Avoma](https://composio.dev/toolkits/avoma) - Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Bland AI](https://composio.dev/toolkits/bland_ai) - Bland AI is a conversational AI platform for building voice agents, phone calls, messaging, and communication workflows. Use it to automate calling, evaluate conversations, and run voice operations at scale.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Past.dev MCP?

With a standalone Past.dev MCP server, the agents and LLMs can only access a fixed set of Past.dev tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Past.dev and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with ChatGPT?

Yes, you can. ChatGPT fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Past.dev tools.

### Can I manage the permissions and scopes for Past.dev while using Tool Router?

Yes, absolutely. You can configure which Past.dev scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Past.dev data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)