Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
StackOne's Talend MCP server gives AI agents 60 ready-to-use actions for Talend — with built-in authentication, security, governance, token efficiency, and high tool-calling accuracy.
Coverage
Create, read, update, and delete across Talend — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Talend MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Talend tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Talend call.
Tools Discovery →A Talend MCP server lets AI agents read and write Talend data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Talend MCP server ships with 60 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from Talend's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create a new environment with an initial workspace via POST /orchestration/environments.
Retrieve all environments configured in Talend Cloud with optional FIQL filtering via GET /orchestration/environments.
Update the name, description, or cloud container limit of an environment via PUT /orchestration/environments/{environmentId}.
Permanently remove an environment and all its contents via DELETE /orchestration/environments/{environmentId}.
Create a new reusable connection with credentials and configuration via POST /orchestration/connections.
Retrieve all connections with optional filtering by environment, workspace, or name via GET /orchestration/connections.
Retrieve full details of a specific connection via GET /orchestration/connections/{connectionId}.
Modify the name or configuration parameters of an existing connection via PUT /orchestration/connections/{connectionId}.
Move a connection to a different workspace within the same environment via PUT /orchestration/connections/{connectionId}/move/{targetWorkspaceId}.
Permanently remove a connection and its stored credentials via DELETE /orchestration/connections/{connectionId}.
Create a new user group for organizing users and managing permissions collectively via POST /account/groups.
Retrieve all user groups with optional name filtering and pagination via GET /account/groups.
Retrieve detailed information about a specific user group via GET /account/groups/{id}.
Rename an existing user group via a partial PATCH /account/groups/{id} update.
Permanently remove a user group from the account via DELETE /account/groups/{id}.
Register a new remote engine in an environment for on-premises job execution via POST /processing/runtimes/remote-engines.
Retrieve all remote engines registered in the account with optional FIQL filtering via GET /processing/runtimes/remote-engines.
Retrieve detailed information about a specific remote engine via GET /processing/runtimes/remote-engines/{id}.
Retrieve all remote engine clusters for high-availability and load balancing via GET /processing/runtimes/remote-engine-clusters.
Retrieve detailed information about a specific remote engine cluster via GET /processing/runtimes/remote-engine-clusters/{clusterId}.
Create a new orphan schedule with an initial trigger in a specified environment via POST /orchestration/schedules.
Duplicate a schedule with all its triggers into a new orphan schedule via POST /orchestration/schedules/{scheduleId}.
Retrieve all schedules with filtering by environment, description, and binding status via GET /orchestration/schedules.
Retrieve complete details of a schedule including all triggers and binding status via GET /orchestration/schedules/{scheduleId}.
Delete an orphan schedule via DELETE /orchestration/schedules/{scheduleId} (only unbound schedules can be deleted).
Add a new trigger to an existing schedule via POST /orchestration/schedules/{scheduleId}/triggers (max 15 per schedule).
Update an existing trigger's configuration within a schedule via PUT /orchestration/schedules/{scheduleId}/triggers.
Remove a specific trigger from a schedule via DELETE /orchestration/schedules/{scheduleId}/triggers by trigger name.
Create a new executable task in a workspace with artifact binding via POST /orchestration/executables/tasks.
Retrieve all available tasks with filtering by environment, runtime, workspace, and artifact via GET /orchestration/executables/tasks.
Create a new multi-step plan to orchestrate task workflows via POST /orchestration/executables/plans.
Retrieve all available plans with filtering by environment, workspace, task, and plan ID via GET /orchestration/executables/plans.
Create a new user account with profile details and optional invitation email via POST /account/users.
Retrieve a paginated list of all users with profile details and role assignments via GET /account/users.
Retrieve the full profile, access details, and role assignments for a specific user via GET /account/users/{id}.
Update an existing user's profile via a full replacement PUT /account/users/{id} request.
Permanently delete a user account and revoke all access immediately via DELETE /account/users/{id}.
Create a new custom role with a name and optional permission assignments via POST /account/roles.
Retrieve all available roles with optional name filtering and pagination via GET /account/roles.
Retrieve the full definition of a specific role including all permission identifiers via GET /account/roles/{id}.
Update an existing custom role's name or permissions via full replacement PUT /account/roles/{id}.
Permanently delete a custom role and unassign it from all users via DELETE /account/roles/{id}.
Create a new Custom workspace within an environment via POST /orchestration/workspaces.
Retrieve all workspaces with optional FIQL query filtering via GET /orchestration/workspaces.
Modify configuration of an existing workspace via PUT /orchestration/workspaces/{id} including name, owner, and artifact protection.
Permanently remove a Custom workspace and cascade delete all contents via DELETE /orchestration/workspaces/{id}.
Add one or more users to a group via POST /account/groups/{id}/users, granting group-level permissions immediately.
Retrieve all users belonging to a specific group via GET /account/groups/{id}/users with pagination.
Retrieve profile information about the currently authenticated user or service account via GET /account/me.
Retrieve plan execution history with filtering by time range, status, environment, and workspace via GET /processing/executables/plans/executions.
Retrieve all available artifacts with filtering by environment, workspace, name, and type via GET /orchestration/artifacts.
Retrieve all roles directly assigned to a specific user via GET /account/users/{id}/roles with pagination.
Retrieve all users assigned a specific role via GET /account/roles/{id}/users with pagination.
Update the functional description of a schedule via PATCH /orchestration/schedules/{scheduleId} without modifying triggers.
Remove a specific user from a group via DELETE /account/groups/{id}/users/{userId}, revoking group-level permissions.
Remove a specific user from a role via DELETE /account/roles/{id}/users/{userId}, revoking the role's permissions.
Preview upcoming triggered events for a schedule within a time range via GET /orchestration/schedules/{scheduleId}/events.
Assign one or more roles to a user via POST /account/users/{id}/roles, granting all associated permissions immediately.
Remove a specific role from a user via DELETE /account/users/{id}/roles/{roleId}, revoking associated permissions.
Bulk assign a role to multiple users in a single POST /account/roles/{id}/users operation.
One endpoint. Any framework. Your agent is talking to Talend in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}144+ actions
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.