← All integrations

VectorShift MCP server

11 operations0 webhooks

AI pipelines and agents with VectorShift - run pipelines singly or in bulk, create them from a graph, create and query knowledge bases, run chatbots, and execute Python transformations in VectorShift's sandbox.

Use VectorShift in Claude, ChatGPT, Cursor or another MCP client

Connect VectorShift once in Corsair, then add one MCP address to your agent.

Connect VectorShift
Setup steps for Claude, ChatGPT, Cursor and Claude Code

Building your own app on the Corsair SDK? Get API keys

Try VectorShift with your agent

Connect VectorShift, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.

Using Corsair, show me what you can do in VectorShift on my account, then run one read-only example and show me the result.

Runs once, when you ask

VectorShift tools and triggers

Tools are what your agent can do in VectorShift through Corsair's MCP server. Triggers are the VectorShift events a routine can start from.

Pipelines

  • Bulk RunWrite

    Run one pipeline once per entry in parallel, with separate inputs and a run id each

    pipelines.bulkRun

  • CreateWrite

    Create a pipeline from a builder graph, passed through unchanged

    pipelines.create

  • ListRead-only

    List pipeline ids, optionally including shared pipelines and the full objects

    pipelines.list

  • RunWrite

    Run a pipeline with the given inputs and read back every output node value

    pipelines.run

Knowledge Bases

  • CreateWrite

    Create a knowledge base, choosing the file parser, chunk size and overlap

    knowledgeBases.create

  • GetRead-only

    Read one knowledge base by id, or by name with an optional owner

    knowledgeBases.get

  • QueryRead-only

    Ask one or more questions of a knowledge base, with retrieval, reranking and answering switches

    knowledgeBases.query

Chatbots

  • CreateWrite

    Create a chatbot over a pipeline, naming the input and output nodes its messages use

    chatbots.create

  • RunWrite

    Send a text or audio message to a chatbot and read its reply, continuing a conversation by id

    chatbots.run

Transformations

  • CreateWrite

    Create a transformation from a Python function and its input and output schemas

    transformations.create

  • RunWrite

    Run a transformation in VectorShift's sandbox with the given arguments

    transformations.run

Connect VectorShift to Claude, ChatGPT or Cursor

  1. 1

    Connect VectorShift in Corsair

    Add your VectorShift API key once in Corsair. Corsair stores the credential encrypted and makes the VectorShift API calls for your agent, so it never goes into a prompt or a config file. Connect VectorShift

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs VectorShift. On a ChatGPT personal plan, connect VectorShift here first.

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp
    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    Codex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client

  3. 3

    Sign in and choose what needs your approval

    Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. None of VectorShift's operations are destructive, so in the default Cautious mode they all run right away. Strict mode asks before each of its 8 writes, and Read mode allows reads only.

FAQ

Install corsair and @corsair-dev/vectorshift, add the VectorShift plugin, and connect with an API key. Then call methods like corsair.vectorshift.api.chatbots.create() from your app. Corsair keeps each tenant isolated.

Yes. VectorShift requires an API key from your VectorShift account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.

Yes. One Corsair client can hit VectorShift, GitHub, Notion, Stripe, and the rest. Trigger VectorShift from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.

Teams use Corsair for AI pipelines and agents with VectorShift - run pipelines singly or in bulk, create them from a graph, create and query knowledge bases, run chatbots, and execute Python transformations in VectorShift's sandbox. Common builds include sync jobs, admin tooling, and agents that call VectorShift APIs from your backend.

The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per VectorShift API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.

We maintain @corsair-dev/vectorshift in the open repo. When VectorShift ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.

No. Corsair does not read your VectorShift data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store VectorShift data on your behalf.

Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.

Yes. Put VectorShift on a link in Strict mode and every write waits for your approval, while destructive actions are refused. None of the VectorShift operations are destructive, so the default Cautious mode runs them all without asking. You can change a link's mode at hub.corsair.dev/me.