Skip to main content
This connector is deprecated. Use Knowledges instead.Knowledges covers the same knowledge-base surface with the current naming (knowledges, documents, webSources instead of vectorStores and vectorStoreFiles). Like this connector, it needs no third-party credential. Install it for any new agent or automation, and migrate the existing ones when convenient.This page is kept for the workspaces that still run the Storage connector. It stays functional, and remains the only connector exposing the administrative surface (per-store API keys, RBAC access bindings, agent skills and admin diagnostics), which Knowledges does not cover. The former files tool and its file instructions (listFiles, uploadFile, getFile, deleteFile, downloadFileContent) have been removed: upload the file to the platform, attach it with vectorStoreFiles.add, and use vectorStoreFiles.list, get, delete and getSourceUrl from there.
The Prisme.ai Storage app is a client connector to the Prisme.ai Storage backend (the slug:storage workspace running in the current environment). It can be consumed two ways: as a remote MCP server that Agent Creator agents call as tools, or as a Builder app whose instructions you call directly from DSUL automations. It exposes the Storage REST API (vector stores, vector-store files, web crawling, RBAC access bindings, per-store API keys, agent skills and admin diagnostics) grouped into 7 entity tools covering 34 operations. Unlike third-party SaaS connectors, this connector requires no credential to paste. Installing the app generates two read-only values in the app instance configuration: the MCP Endpoint (a shared endpoint served by the platform’s Storage connector workspace) and an MCP API Key signed for your workspace. The agent capability sends that key in the mcp-api-key header; the key identifies the installing workspace. The connector propagates the caller’s Prisme.ai identity to the Storage backend over the platform’s cross-workspace forward-auth mechanism: every call inherits the user × workspace permissions of whoever triggered it, and the Storage backend enforces its own RBAC bindings on top. The capability Scope context_id,agent_id,user_id carries the agent and user context. The connector has no per-agent allowlist.

Vector Stores & RAG

Create vector stores, attach files (an uploaded platform file or a URL), download their sources, trigger reindex, run semantic search, monitor crawling.

Access, Keys & Skills

Grant/revoke RBAC bindings per principal, create and rotate per-store API keys, manage reusable agent skills.

Who is this for?

This connector is used by three different roles. Jump to the section that matches yours; each one is self-contained.

Agent builder

You build agents in Agent Creator and want them to manage files, vector stores and RAG. → Agent builder tab.

Platform admin

You run the platform and want to expose Storage as a reusable capability once for everyone. → Platform admin setup accordion below.

Workspace builder

You write Builder automations (DSUL) that call Storage instructions directly. → Workspace builder tab.

Prerequisites

  • A Prisme.ai workspace with the Prisme.ai Storage app installed.
  • The Storage backend ships pre-wired to the current environment (sandbox or prod); there is no baseUrl, service URL or API token to configure. The connector resolves the Storage workspace via slug:storage and forwards the caller’s authentication automatically.
  • The end user (or agent’s calling user) must hold the appropriate role on the target vector store / file:
    • viewer: read files, list vector stores, run semantic search.
    • contributor: add/remove files in a vector store, trigger recrawls.
    • owner: manage access bindings, API keys and skills; delete vector stores.
    • admin (platform admin): admin.getStats, admin.healthCheck, cross-workspace listings (scope=all).
  • For URL-based ingestion (vectorStoreFiles.add with url=…), the URL must be reachable from the Storage backend (a public URL or a Prisme.ai share_token).
No third-party credential. This connector carries no third-party API key; each workspace installs the app, receives its own MCP API Key automatically, and the caller’s Prisme.ai identity is forwarded to the Storage backend. The platform operator maintains the signing secret (App HMAC Secret) of the central Storage connector workspace only; there is no per-tenant credential to provision.
The only optional one-time task is to expose Storage as a reusable capability in AI Governance, so agent builders can enable it from the capability picker instead of pasting an MCP endpoint URL.

Declare the capability in AI Governance

1

Open AI Governance > Capabilities

Create (or edit) a Prisme.ai Storage capability.
2

Point it at the MCP endpoint

Set the capability’s MCP server URL to the connector’s MCP Endpoint (read from the installed app instance), add an auth header named mcp-api-key whose value is the MCP API Key of that app instance, and set its Scope to:
The key identifies the workspace whose app instance the capability uses; without it, every tool call is refused.
3

Make it available to agent builders

Once created, the capability appears in the capability picker for agent builders in your organization. Access to the catalog follows your organization’s existing roles; there is no per-capability role grant for this connector.
4

Smoke-test

From an agent that has the capability, ask it to list vector stores or files. The call runs as the agent’s user, and the Storage backend returns only the resources that user can see.
Declaring the capability makes the connector available; it does not by itself authorize a specific agent against any data. Authorization is enforced by the Storage backend’s own RBAC bindings, evaluated against the forwarded caller identity: a user (or agent’s user) only ever sees the stores and files they hold a role on. There is no OAuth auth-config JSON to attach in Governance: authentication is the forwarded Prisme.ai identity, not a per-user OAuth flow.

Agent builder

Goal: let an agent you build in Agent Creator manage files, vector stores and RAG through the Storage MCP tools.
Before an agent can call the connector, a Workspace builder must have installed the Prisme.ai Storage app in a workspace (see the Workspace builder tab), or a Platform admin must have published the capability in AI Governance (see the Platform admin setup accordion above).
The capability authenticates to the connector with the MCP API Key of your workspace’s app instance, sent in the mcp-api-key header. The connector forwards the caller’s Prisme.ai identity to the Storage backend, which enforces its own RBAC bindings against that user. The key is configured on the capability, never in the agent prompt.
1

Get the MCP endpoint

Install the Prisme.ai Storage app in your workspace (see the Workspace builder tab) and copy its MCP Endpoint and MCP API Key from the app instance configuration. If a Platform admin already published the capability, you can skip straight to the capability picker.
2

Add the capability to your agent

In your agent, add a capability pointing at the MCP Endpoint URL (or pick the published Prisme.ai Storage capability from the catalog), add an auth header named mcp-api-key with the MCP API Key value, and set its Scope to:
Without the mcp-api-key header, every tool call is refused with Missing required header: mcp-api-key.
3

Use it

Ask the agent to manage files or knowledge; it calls the Storage tools, and every call is scoped to what the calling user is allowed to see.

Brief the agent in its system prompt

Wiring the capability is not enough; the agent must know the tools exist and when to reach for them. Copy-pasteable starter:
Refine the trigger keywords (resource names, business domains, typical user phrasings) so the agent reliably picks up the right intent in your context.
Legacy AI Knowledge agents (no native MCP picker): add the connector under Advanced > Tools > MCP, paste the MCP Endpoint URL and send the MCP API Key in the mcp-api-key header. The agent’s identity is still propagated so the Storage backend can resolve the caller’s RBAC.

Available Tools

The MCP server exposes 7 entity-level tools, each with an action argument that selects the operation. Every tool also accepts an outputFormat argument (verbose default / structured / both).

vectorStores

vectorStoreFiles

crawling

access

apiKeys

skills

admin

Output Formats

Every tool accepts an outputFormat argument that controls the MCP response shape:
  • verbose (default): human-readable text optimized for LLM consumption.
  • structured: machine-readable JSON in structuredContent.
  • both: the structured payload, with its JSON also rendered as text.

Tool Details

vectorStores (action: create)

vectorStoreFiles (action: add)

access (action: grant)

apiKeys (action: create)

The plaintext API-key secret is returned only at creation time. Store it securely; the platform keeps only a hash.

Error Handling

Common Issues

“Missing required header: mcp-api-key”: The agent capability does not send the key. Add an auth header named mcp-api-key with the MCP API Key value of your app instance, save the agent, and retry. “Invalid API key”: The capability sends a key that is not valid, for example a key copied from another app instance or truncated. Copy the MCP API Key again from your app instance configuration, update the header, and retry. “Credentials lookup failed”: The connector could not resolve the app instance that the key was issued for, for example because the app was uninstalled or reinstalled since the key was copied. Open the app instance configuration, copy the current MCP API Key, update the capability header, and retry. “Anonymous request rejected” (401): The caller’s Prisme.ai identity did not make it through to the Storage backend. This usually means the call is being made from a tool client that does not propagate the workspace identity. Use the Agent Creator capability or call from a DSUL automation (both forward identity correctly), or pass an explicit accessToken override. Forbidden on a store you can see (403): Listing a store does not imply write access. The operation requires a higher role (e.g. contributor to add files, owner to grant access or manage keys). Ask the store owner to grant the right binding via access.grant. addFileToVectorStore ignored my file_name when using url: URL-based ingestion of vector-store files drops the file_name argument. For filename control, upload the file to the platform first and then add it via vectorStoreFiles.add with its id as file_id. force_recrawl had no effect: Also pass the original url argument; the backend keys recrawl identity off the URL, not the file_id. Empty list when listing vector stores: By default listVectorStores returns only scope: own. Add scope: shared to include stores shared with you, or scope: all if you are a platform admin.

External Resources

RAG & Vector Stores

How vector stores, embeddings and the RAG crawling pipeline work in Prisme.ai.

Tool Agents

Learn how Agent Creator agents consume MCP tools and capabilities.