# How to connect PredictHQ to Claude

```json
{
  "title": "How to connect PredictHQ to Claude",
  "toolkit": "PredictHQ",
  "toolkit_slug": "predicthq",
  "framework": "Claude Cowork",
  "framework_slug": "claude-cowork",
  "url": "https://composio.dev/toolkits/predicthq/framework/claude-cowork",
  "markdown_url": "https://composio.dev/toolkits/predicthq/framework/claude-cowork.md",
  "updated_at": "2026-11-21T05:31:31.388Z"
}
```

## Introduction

Claude is Anthropic's AI assistant, available on the web, in the desktop app, and on mobile. Cowork is its agent for knowledge work, and it runs on all of those surfaces too. Connected to your apps, Claude can work with your files and services to accomplish complex tasks on your behalf.
This guide walks you through the easiest and most secure way to connect your PredictHQ account to Claude via Composio Connect, enabling it to find major events near San Francisco, forecast demand around upcoming concerts, compare event impact across retail locations, and more such actions on your behalf without compromising your account security.
Setup is the same on Claude Web, Desktop, and Cowork, and you only need to do it once. The connector is tied to your account, so it's available in all three.
For exact tool slugs and parameter tables, see the [tool catalog in the Composio docs](https://docs.composio.dev/toolkits/predicthq).

## Also integrate PredictHQ with

- [ChatGPT](https://composio.dev/toolkits/predicthq/framework/chatgpt)

## Connect PredictHQ to Claude Cowork

### Connecting PredictHQ to Claude Web, Desktop, and Cowork
Two ways to add the Composio connector. Pick whichever you prefer.
### 1. Add with one click
Click the button. Claude opens with the Composio connector filled in. Click Add, then go to step 2.
[Add to Claude](https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Composio&connectorUrl=https%3A%2F%2Fconnect.composio.dev%2Fmcp)
### Add manually
In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.
Click Add custom connector and paste in the Composio MCP server URL:

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

## What is the PredictHQ MCP server, and what's possible with it?

The PredictHQ MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your PredictHQ account. It provides structured and secure access to event intelligence, demand forecasting, and location analytics, so your agent can count relevant events, identify demand surges, create and review forecasts, assess event impact areas, and manage community event submissions on your behalf.
- Event intelligence: Have your agent count events and broadcasts using filters for dates, locations, categories, attendance, rank, and other event details.
- Demand surge detection: Let the agent identify dates with significant predicted demand surges for a specified location and report the expected event attendance.
- Forecast planning: Direct your agent to create forecast models for saved business locations, review their readiness and accuracy, inspect uploaded demand data, and retrieve generated forecast results.
- Location impact analysis: Instruct your agent to calculate predicted event impact areas as GeoJSON, create reusable saved locations, and manage their opening hours and closure periods.
- Event feedback and submissions: Have your agent create hosted Loop links, review submitted events and feedback conversations, inspect link settings, and manage existing links.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `PREDICTHQ_CALCULATE_EVENT_FEATURES` | Calculate Event Features | Calculate one page of daily or weekly ML-ready event features for a required date range using either a Beam analysis or a manually configured location and feature set. |
| `PREDICTHQ_COUNT_BROADCASTS` | Count Broadcasts | Return the total number of PredictHQ broadcast records matching optional broadcast, schedule, date, viewership, location, and event filters, without returning result records. |
| `PREDICTHQ_COUNT_EVENTS` | Count Events | Get aggregate event counts by category, label, rank level, and the same date, location, rank, attendance, spend, and event filters supported by search. |
| `PREDICTHQ_CREATE_BEAM_ANALYSIS` | Create Beam Analysis | Create a Beam analysis that correlates an owned location's events with uploaded demand data. |
| `PREDICTHQ_CREATE_BEAM_ANALYSIS_GROUP` | Create Beam Analysis Group | Create a Beam analysis group that aggregates feature importance across compatible analyses. |
| `PREDICTHQ_CREATE_FORECAST_MODEL` | Create Forecast Model | Create a forecast model for a Saved Location. After creation, upload historical demand data and trigger model training with the corresponding Forecasts actions. |
| `PREDICTHQ_CREATE_LOOP_LINK` | Create Loop Link | Create a hosted Loop link for end users to submit missing events or event feedback, and return both shareable URLs. An empty body creates a default-named active link. |
| `PREDICTHQ_CREATE_SAVED_LOCATION` | Create Saved Location | Create a reusable PredictHQ Saved Location from an exact business point, a custom GeoJSON area, or Geonames place IDs. |
| `PREDICTHQ_CREATE_SAVED_LOCATION_CLOSURE` | Create Saved Location Closure | Create a closure period for a PredictHQ Saved Location. The date range must not overlap an existing closure for the location. |
| `PREDICTHQ_CREATE_SAVED_LOCATION_OPENING_HOURS` | Create Saved Location Opening Hours | Create opening hours for a Saved Location. The effective date range must not overlap another opening-hours record for the same location. |
| `PREDICTHQ_DELETE_BEAM_ANALYSIS` | Delete Beam Analysis | Soft-delete a Beam Analysis. The analysis remains retrievable when filtering for deleted analyses, and containing Analysis Groups are refreshed automatically. |
| `PREDICTHQ_DELETE_BEAM_ANALYSIS_GROUP` | Delete Beam Analysis Group | Delete an existing Beam Analysis Group without deleting the individual analyses in the group. |
| `PREDICTHQ_DELETE_FORECAST_MODEL` | Delete Forecast Model | Permanently deletes a forecast model and all associated demand data and forecasts. The model must not be in `preparing`, `training`, or `forecasting` status. This action is irreversible. |
| `PREDICTHQ_DELETE_LOOP_LINK` | Delete Loop Link | Soft-delete a Loop link. The record remains retrievable with `status=deleted`. |
| `PREDICTHQ_DELETE_SAVED_LOCATION` | Delete Saved Location | Permanently delete a Saved Location and all of its associated insights data. This action is irreversible. |
| `PREDICTHQ_DELETE_SAVED_LOCATION_CLOSURE` | Delete Saved Location Closure | Delete a closure by ID from the specified PredictHQ Saved Location. This action is irreversible. |
| `PREDICTHQ_DELETE_SAVED_LOCATION_OPENING_HOURS` | Delete Saved Location Opening Hours | Delete an opening hours record by ID from the specified PredictHQ Saved Location. This action is irreversible. |
| `PREDICTHQ_GET_BEAM_ANALYSIS` | Get Beam Analysis | Return the full details of one Beam Analysis, including its location, demand type, rank, readiness status, and processing state. |
| `PREDICTHQ_GET_BEAM_ANALYSIS_FEATURE_IMPORTANCE` | Get Beam Analysis Feature Importance | Return the Beam feature groups whose statistical significance indicates how strongly they affect an analysis's demand, including the Features API fields recommended for forecasting models. |
| `PREDICTHQ_GET_BEAM_ANALYSIS_GROUP` | Get Beam Analysis Group | Return the full details of one Beam Analysis Group, including its member analyses, demand type, readiness status, and processing state. |
| `PREDICTHQ_GET_BEAM_ANALYSIS_GROUP_FEATURE_IMPORTANCE` | Get Beam Analysis Group Feature Importance | Return feature-importance results aggregated across the analyses in an existing Beam Analysis Group, including each feature group's Features API fields and p-value. |
| `PREDICTHQ_GET_DEMAND_SURGES` | Get Demand Surges | Return dates with at least the requested demand-surge intensity for a required date and location, including summed predicted attendance. |
| `PREDICTHQ_GET_FORECAST_MODEL` | Get Forecast Model | Retrieves a forecast model by ID, including its readiness status, configuration, accuracy metrics, and location details. |
| `PREDICTHQ_GET_LOOP_LINK` | Get Loop Link | Return one Loop Link, including its status, metadata, expiry, and hosted event-submission and event-feedback URLs. |
| `PREDICTHQ_GET_LOOP_SETTINGS` | Get Loop Settings | Return the organization name displayed in the hosted Loop interface. |
| `PREDICTHQ_GET_PREDICTED_IMPACT_AREA` | Get Predicted Impact Area | Calculate a polygonal or radial Predicted Impact Area for a business location and industry, returned as GeoJSON. |
| `PREDICTHQ_GET_SAVED_LOCATION` | Get Saved Location | Retrieve a Saved Location by ID, including its geometry, enrichment status, labels, resolved places, summary insights, opening hours, and closures. |
| `PREDICTHQ_GET_SAVED_LOCATION_CLOSURE` | Get Saved Location Closure | Return a single closure by ID for the specified Saved Location. |
| `PREDICTHQ_GET_SAVED_LOCATION_OPENING_HOURS` | Get Saved Location Opening Hours | Return one opening hours record by its ID for a specified PredictHQ Saved Location. |
| `PREDICTHQ_LIST_BEAM_ANALYSES` | List Beam Analyses | Return one page of Beam Analyses, with filters for lifecycle state, readiness, groups, demand type, location, labels, update date, and name. |
| `PREDICTHQ_LIST_BEAM_ANALYSIS_CORRELATION_RESULTS` | List Beam Analysis Correlation Results | Return one page of results correlating PredictHQ event data with an analysis's transactional demand data for a required lower and upper date bound. |
| `PREDICTHQ_LIST_BEAM_ANALYSIS_GROUPS` | List Beam Analysis Groups | Return one page of Beam Analysis Groups, optionally filtered by update date, name, lifecycle state, readiness, demand interval, or industry. |
| `PREDICTHQ_LIST_FORECAST_ALGORITHMS` | List Forecast Algorithms | Returns the list of available forecasting algorithms. Currently one algorithm is offered (`phq-xgboost`) based on XGBoost. |
| `PREDICTHQ_LIST_FORECAST_MODEL_DEMAND` | List Forecast Model Demand | Return one page of demand data uploaded to a forecast model, optionally filtered by date, as JSON, CSV, or newline-delimited JSON. |
| `PREDICTHQ_LIST_FORECAST_MODELS` | List Forecast Models | Return one page of forecast models belonging to the authenticated organization, optionally filtered by text, Saved Location, or readiness status. |
| `PREDICTHQ_LIST_LOOP_EVENT_SUBMISSIONS` | List Loop Event Submissions | Return one page of Loop-submitted events matching link, event, user, review, state, category, location, and date filters. |
| `PREDICTHQ_LIST_LOOP_FEEDBACK_CONVERSATIONS` | List Loop Feedback Conversations | Return one page of Loop feedback conversations matching record, link, user, feedback type, status, text, and date filters. |
| `PREDICTHQ_LIST_LOOP_LINKS` | List Loop Links | Return one page of hosted Loop links matching text, link, user, and sort filters. |
| `PREDICTHQ_LIST_MODEL_FORECAST_RESULTS` | List Model Forecast Results | Return one page of generated forecast results for a trained model, optionally filtered by date and enriched with features or event explainability. |
| `PREDICTHQ_LIST_PLACE_HIERARCHIES` | List Place Hierarchies | Return one page of administrative hierarchy chains resolved from either place IDs or coordinates. |
| `PREDICTHQ_LIST_SAVED_LOCATION_CLOSURES` | List Saved Location Closures | Return one page of closure records for a PredictHQ Saved Location, optionally filtered by the dates on which the records are active. |
| `PREDICTHQ_LIST_SAVED_LOCATION_INSIGHT_EVENTS` | List Saved Location Insight Events | Return one page of events that impact a specified PredictHQ Saved Location. |
| `PREDICTHQ_LIST_SAVED_LOCATION_OPENING_HOURS` | List Saved Location Opening Hours | Return one page of opening-hours records for a Saved Location, optionally filtered by the dates on which the records are active. |
| `PREDICTHQ_LIST_SAVED_LOCATIONS` | List Saved Locations | Search and return one page of Saved Locations, including reusable location IDs, geographic definitions, enrichment state, and summary insights. |
| `PREDICTHQ_REFRESH_BEAM_ANALYSIS` | Refresh Beam Analysis | Rerun correlation and analysis processing for an existing Beam Analysis. The analysis readiness status becomes pending until processing completes; the request fails if the analysis is already being processed. |
| `PREDICTHQ_REFRESH_BEAM_ANALYSIS_GROUP` | Refresh Beam Analysis Group | Rerun aggregation for an existing Beam Analysis Group. The group's readiness status becomes pending until processing completes; the request fails if the group is already being processed. |
| `PREDICTHQ_REPLACE_BEAM_ANALYSIS` | Replace Beam Analysis | Fully replace an existing Beam analysis using PUT. Retrieve the current analysis first and include every value that must be preserved; omitted optional fields may be lost. Use the partial-update action for PATCH semantics. |
| `PREDICTHQ_REPLACE_BEAM_ANALYSIS_GROUP` | Replace Beam Analysis Group | Fully replace an existing Beam analysis group using PUT. Retrieve the current group first and include all values that must be preserved; use the partial-update action when omitted fields should remain unchanged. |
| `PREDICTHQ_REPLACE_FORECAST_MODEL` | Replace Forecast Model | Fully replace an existing forecast model's mutable configuration. This is the PUT replacement operation, not the partial PATCH update. Configuration changes may make the model stale and require retraining, and are blocked while it is preparing, training, or forecasting. |
| `PREDICTHQ_REPLACE_LOOP_LINK` | Replace Loop Link | Fully replace the mutable name, expiry, and metadata of an existing PredictHQ Loop Link using PUT. |
| `PREDICTHQ_REPLACE_SAVED_LOCATION` | Replace Saved Location | Fully replace an existing PredictHQ Saved Location using PUT. Include every value that must be preserved. To recalculate its Predicted Impact Area, provide origin_geojson without geojson or place_ids. |
| `PREDICTHQ_REPLACE_SAVED_LOCATION_OPENING_HOURS` | Replace Saved Location Opening Hours | Fully replace one PredictHQ Saved Location opening-hours record. This PUT operation replaces the complete record and rejects date ranges that overlap another opening-hours record for the location. |
| `PREDICTHQ_SEARCH_BROADCASTS` | Search Broadcasts | Return one page of US county-level live-TV broadcast records matching event, geography, status, and date filters. |
| `PREDICTHQ_SEARCH_EVENTS` | Search Events | Search for events happening in a location and date range using PredictHQ's event, location, rank, label, attendance, spend, and lifecycle filters. Returns one page and a continuation cursor. |
| `PREDICTHQ_SEARCH_PLACES` | Search Places | Return one page of places matching text, country, coordinates, place IDs, or administrative type filters. |
| `PREDICTHQ_TRAIN_FORECAST_MODEL` | Train Forecast Model | Triggers asynchronous training for a forecast model that has uploaded demand data and is in an eligible readiness state. Poll the model's `readiness.status` field to monitor progress. |
| `PREDICTHQ_UPDATE_BEAM_ANALYSIS` | Update Beam Analysis | Partially update one or more fields on an existing Beam analysis without replacing fields that are omitted. |
| `PREDICTHQ_UPDATE_BEAM_ANALYSIS_GROUP` | Update Beam Analysis Group | Partially update an existing Beam analysis group using PATCH. Only fields provided in the request are changed; use the replacement action to replace all fields. |
| `PREDICTHQ_UPDATE_FORECAST_MODEL` | Update Forecast Model | Partially update a forecast model. Changes to location, demand type, forecast window, algorithm, or baseline generation are blocked while the model is preparing, training, or forecasting, and otherwise make it stale until it is retrained. |
| `PREDICTHQ_UPLOAD_BEAM_ANALYSIS_DEMAND` | Upload Beam Analysis Demand | Upload daily or weekly demand data to an existing Beam analysis. New values replace existing values for matching dates, and individual dates cannot be removed. The complete stored series must remain valid after each upload. |
| `PREDICTHQ_UPLOAD_FORECAST_MODEL_DEMAND` | Upload Forecast Model Demand | Upload historical demand data to an existing forecast model as typed JSON, CSV, or newline-delimited JSON. The upload changes the model's training data and requires paid Forecasts access. |
| `PREDICTHQ_UPSERT_LOOP_SETTINGS` | Upsert Loop Settings | Create or replace the organization-wide display name used by the hosted Loop interface. WARNING: this changes the Loop UI for the entire organization. Read and save the current settings first, obtain explicit approval, and have an unconditional restoration plan before calling. |

## Supported Triggers

None listed.

## Troubleshooting

### 1. Why does Claude not use the Composio connector for PredictHQ?

The connector can show as connected, but Claude must use it in each PredictHQ conversation.
- Click + at the lower left of the chat, or type /.
- Hover Connectors.
- Turn on Composio.
- Ask Claude to connect to PredictHQ again.

### 2. Why does Claude show an MCP server error before PredictHQ connects?

Claude can show Couldn't reach the MCP server or Authorization with the MCP server failed when you add the connector for PredictHQ.
- Check that the connector URL is https://connect.composio.dev/mcp.
- Connectors run from Anthropic's cloud, so your device network is usually not the problem.
- Add the connector again from Customize > Connectors, then ask Claude to connect PredictHQ.
- If it fails again, send the error and the ofid_ reference id to support@composio.dev.

### 3. Why does the PredictHQ authorization link not work?

The Composio connector is one server. Your PredictHQ account connects separately when Claude asks for it.
- If the browser does not open, or the link expires, ask Claude to retry the PredictHQ connection.
- Composio creates a fresh PredictHQ authorization link.
- Open that link in your browser and finish the PredictHQ sign-in.

### 4. Why do PredictHQ actions fail after they worked before?

The PredictHQ connection can expire or lose permission.
- Ask Claude to inspect the PredictHQ connection.
- If the connection is unhealthy, disconnect it when Claude prompts you.
- Reconnect the PredictHQ account and retry the action.
- If Claude shows a permission prompt, approve it before Claude changes data in PredictHQ.
- If the action still fails with a permission error, check that the connected account has that permission in PredictHQ itself.

### 5. How do I switch to a different PredictHQ account?

Claude can manage the PredictHQ connection for you.
- Ask Claude to disconnect or delete the current PredictHQ account.
- Ask Claude to connect PredictHQ again.
- Open the new Composio authorization link for PredictHQ.
- Sign in with the other PredictHQ account in the browser.
- After the account connects, ask Claude to retry the PredictHQ task.

### 6. Why is my PredictHQ connection missing in Claude Desktop or on a Team plan?

The connector belongs to your Claude account, so your PredictHQ connection works in Claude Web, Desktop, and Cowork.
- In Claude Desktop, open Customize > Connectors.
- Next to Composio, click ⋮ and click Clear cache.
- If PredictHQ tools still do not appear, click ⋮, disconnect, remove the connector, and add it again.
- On Team or Enterprise, an Owner or Primary Owner must enable the connector before you can connect PredictHQ.

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

The PredictHQ MCP server connects Claude Web, Desktop, and Cowork to your PredictHQ account through Composio. Once connected, Claude can use the available PredictHQ tools and triggers to complete tasks on your behalf.

## Complete Code

None listed.

## How to build PredictHQ MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/predicthq/framework/chatgpt)

## Related Toolkits

- [Firecrawl](https://composio.dev/toolkits/firecrawl) - Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources.
- [Tavily](https://composio.dev/toolkits/tavily) - Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research.
- [Serpapi](https://composio.dev/toolkits/serpapi) - SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research.
- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [Peopledatalabs](https://composio.dev/toolkits/peopledatalabs) - Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data.
- [Snowflake](https://composio.dev/toolkits/snowflake) - Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds.
- [Posthog](https://composio.dev/toolkits/posthog) - PostHog is an open-source analytics platform for tracking user interactions and product metrics. It helps teams refine features, analyze funnels, and reduce churn with actionable insights.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [0xArchive](https://composio.dev/toolkits/0xarchive) - 0xArchive is a crypto data service for historical and current market data, quality signals, feedback, and webhooks. It helps teams access reliable crypto data and manage REST integrations from one API.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [AccuWeather](https://composio.dev/toolkits/accu_weather) - AccuWeather is a global weather service providing current conditions, forecasts, MinuteCast precipitation, alerts, and lightning data. Use it for fast, localized forecasts and real-time weather alerts.
- [Adafruit IO](https://composio.dev/toolkits/adafruit_io) - Adafruit IO is Adafruit's cloud platform for connected device and IoT project data. It helps you store, visualize, and act on sensor feeds without running your own backend.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agentql](https://composio.dev/toolkits/agentql) - Agentql is a toolkit that connects AI agents to the web using a specialized query language. It enables structured web interaction and data extraction for smarter automations.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ahrefs MCP](https://composio.dev/toolkits/ahrefs_mcp) - Ahrefs MCP is Ahrefs' hosted MCP server for SEO data and insights. Use it to access backlinks, organic metrics, keyword research, and competitor analysis.
- [Akta](https://composio.dev/toolkits/akta) - Akta is a company intelligence platform providing enrichment, news, and alternative business signals. It helps teams build targeted company lists and enrich data-driven workflows.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Amplitude](https://composio.dev/toolkits/amplitude) - Amplitude is a digital analytics platform for product and behavioral data insights. It helps teams analyze user journeys and make data-driven decisions quickly.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and PredictHQ MCP?

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

### Can I use Tool Router MCP with Claude Cowork?

Yes, you can. Claude Cowork 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 PredictHQ tools.

### Can I manage the permissions and scopes for PredictHQ while using Tool Router?

Yes, absolutely. You can configure which PredictHQ 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 PredictHQ data and credentials are handled as safely as possible.

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