Palantir Foundry

Live

Palantir Foundry integration — ontology objects, datasets, SQL queries, orchestration, AIP agents, and admin.

What is Palantir Foundry?

Full Palantir Foundry REST API integration with 92 methods covering Ontology (objects, actions, queries, links, time series), Datasets (CRUD, branches, files, transactions), SQL queries, Orchestration (builds, schedules), Admin (users, groups), AIP Agents (sessions, RAG), Streams, Connectivity, and Filesystem. Bearer token (PAT) authentication.

Available Tools

listOntologies
List all ontologies in the Foundry stack
getOntology
Get ontology details by RID
getOntologyFullMetadata
Get full ontology metadata including all types
listObjectTypes
List all object types in an ontology
getObjectType
Get object type definition and properties
getObjectTypeFullMetadata
Get full object type metadata
listOutgoingLinkTypes
List link types for an object type
listObjects
List objects of a specific type with pagination
getObject
Get a single object by primary key
searchObjects
Search objects with where filters and ordering
aggregateObjects
Aggregate objects (count, sum, avg, min, max)
countObjects
Count objects matching a filter
listLinkedObjects
List objects linked to a source object
getLinkedObject
Get a specific linked object by key
listActionTypes
List all action types in an ontology
getActionType
Get action type definition and parameters
applyAction
Apply an action (create/update/delete objects)
applyActionBatch
Apply an action in batch mode
listQueryTypes
List all query types in an ontology
executeQuery
Execute an ontology query with parameters
getTimeSeriesFirstPoint
Get first time series data point for an object property
getTimeSeriesLastPoint
Get latest time series data point
streamTimeSeriesPoints
Stream time series points for a date range
getAttachment
Get attachment metadata by RID
uploadAttachment
Upload a new attachment
createDataset
Create a new dataset
getDataset
Get dataset details
getDatasetSchema
Get dataset schema (columns, types)
readDataset
Read dataset contents
listBranches
List branches on a dataset
getBranch
Get branch details
createBranch
Create a dataset branch
deleteBranch
Delete a dataset branch
createTransaction
Create a dataset transaction for writes
getTransaction
Get transaction details
commitTransaction
Commit a transaction
abortTransaction
Abort a transaction
listFiles
List files in a dataset
getFile
Get file metadata
uploadFile
Upload a file to a dataset transaction
deleteFile
Delete a file from a dataset
executeSql
Execute a SQL query (async)
getSqlQueryStatus
Check SQL query execution status
getSqlQueryResults
Get SQL query results
cancelSqlQuery
Cancel a running SQL query
createBuild
Trigger a build for datasets
getBuild
Get build status and details
cancelBuild
Cancel a running build
searchBuilds
Search builds by dataset, branch, or status
getBuildJobs
List jobs within a build
getJob
Get job details
createSchedule
Create a build schedule with cron expression
getSchedule
Get schedule details
deleteSchedule
Delete a schedule
pauseSchedule
Pause a schedule
unpauseSchedule
Unpause a schedule
runSchedule
Trigger a schedule run manually
getScheduleRuns
List runs for a schedule
listUsers
List all users
getUser
Get user details by ID
getCurrentUser
Get the current authenticated user
searchUsers
Search users by name or email
deleteUser
Delete a user
listGroups
List all groups
getGroup
Get group details
createGroup
Create a new group
deleteGroup
Delete a group
listGroupMembers
List members of a group
addGroupMembers
Add members to a group
removeGroupMembers
Remove members from a group
getAgent
Get AIP agent details
listAgentSessions
List sessions for an agent
createAgentSession
Create a new agent session
getAgentSession
Get session details
continueAgentSession
Send a message to continue an agent session
cancelAgentSession
Cancel an agent session
getAgentSessionContent
Get session conversation content
getAgentRagContext
Get RAG context for an agent session
createStream
Create a streaming data pipeline
getStream
Get stream details
publishRecords
Publish records to a stream
getStreamRecords
Read records from a stream
getConnection
Get connection details
createFileImport
Create a file import configuration
getFileImport
Get file import details
executeFileImport
Execute a file import
listFileImports
List file imports for a connection
getFolder
Get folder details
listFolderChildren
List folder contents
createFolder
Create a new folder
getProject
Get project details
createProject
Create a new project

Requirements

Palantir Foundry account
Access to a Palantir Foundry stack
Bearer token required
Generate a PAT at {stack}/workspace/settings/tokens. Enter on the MCP Servers page to connect.

Quick Setup Guide

Follow these steps to connect your AI agents to this connector

In Foundry, go to Settings → Tokens → Create token. Grant appropriate scopes (api:ontologies-read, api:datasets-read, etc.).

Navigate to /mcp, find Palantir Foundry, paste your token and stack hostname (e.g., mycompany.palantirfoundry.com).

Use listOntologies to discover your ontology, then searchObjects or executeSql to query data.

Connect to Your AI Assistant

Choose your AI assistant below for specific setup instructions

Follow these steps to connect Palantir Foundry to Claude:

Step 1: Open Claude Settings

Launch Claude → Click the profile button (bottom left) → Navigate to Settings

Step 2: Access Connectors

Scroll down to the Connectors tab → Navigate to the bottom → Click “Add Custom Connector”

Step 3: Name Your Connector

Enter any name you'd like for this connector

Step 4: Get the Connector URL

Step 5: Add the Connector

Paste the URL in the “Remote MCP Server URL” text box → Click Add

Step 6: Start Using

Your connector is now ready to use in Claude

Follow these steps to connect Palantir Foundry to ChatGPT:

Step 1: Enable Developer Mode

Go to Settings → Connectors → Advanced → Enable Developer mode

Step 2: Create New Connector

Go back to Connectors page → Click “Create” (top right)

Step 3: Name Your Connector

Enter any name you'd like for this connector (descriptions are optional)

Step 4: Get the Connector URL

Step 5: Add the URL

Paste the URL in the “MCP Server URL” text box

Step 6: Set Authentication

Click the authentication dropdown → Select “No authentication” (PatchOps handles authentication internally)

Step 7: Create the Connector

Click “I understand and want to continue” checkbox → Press Create

Step 8: Using the Connector

Start a new chat → Click the + button (left of text box) → Open dropdown → Hover over three dots labeled “More” → Select your connector

Instructions for connecting Palantir Foundry to GitHub Copilot:

Coming Soon

Detailed setup instructions for GitHub Copilot will be added here.

For other MCP-compatible platforms:

Step 1: Get the Connector URL

Step 2: Add to Configuration

Add this configuration to your MCP settings file. Replace the URL with your specific connector URL from the /mcp page:

"Palantir Foundry-MCP": {
  "url": "https://patchops.ai/api/mcp/...",
  "type": "http"
}

Example Configuration

Here’s an example using PatchOps MCP:

"PatchOps-MCP": {
  "url": "https://patchops.ai/api/mcp/...",
  "type": "http"
}