Connect Claude and use Library

All agent connection guides

Hosted Claude connection

The remote connector uses browser authorization with PKCE, one-hour access tokens, and rotating refresh tokens. Approval lasts at most 90 days. Only the selected workspace is authorized. Your account password and Foo Guard API keys are never pasted into Claude.

The whoami tool verifies the connection and returns its Library agent link. Until that call succeeds, the agent is waiting for verification. The report_inventory tool accepts only explicitly approved relative filenames and SHA-256 fingerprints. Do not invent hashes for files the client cannot access. Reporting replaces the previous metadata, and an empty list clears it.

Connection-only grants do not read Library files or run scans. Optional Library permissions are described below. No grant inspects other integrations or monitors conversations. Gateway calls require the separate permission and setup described below. A hosted MCP connection identifies the authorized client connection, not a model version or a unique conversation.

Use Disconnect reporting on the Library agent page to revoke all tokens for that connection. Reauthorize from Claude’s connector settings after expiry or revocation. Reauthorization by the same user and registered client reuses the agent in the selected workspace; a newly registered client can create a separate record. Archive obsolete records if a client re-registers. Do not select the local connector to recover a hosted connection.

If authorization expires or the callback fails, start again in Claude. Check the chosen workspace and callback domain before approval. A real Claude sign-in and successful tool call are required to confirm client interoperability; deployment and protocol tests alone are not that confirmation.

Use Library from your hosted agent

Ask Claude to list your Foo Guard Library configs or skills. If the connection needs additional access, complete a fresh authorization in Claude and select the Library permissions you want. Existing connections keep their original connection-only permissions until you explicitly approve an upgrade. If Claude keeps the old permissions, disconnect and reconnect in its connector settings, then retry.

and administrators may read unpublished drafts for review. This does not approve a file for installation, bypass the published distribution API, or prove use.

Open the returned Foo Guard link and review its workspace, filename and content. Only Save to Library commits it. Prior copies are preserved; a matching copy is reused. Configs are normalized and detected credentials are redacted. The hash represents the retained submitted copy, not an original file on your device. Proposals expire after 15 minutes; at most five may be pending per account.

Scans entry, and returns findings. It uses the workspace's normal scan allowance. No skill code or instructions execute during scanning.

• Read Library lists files and retrieves an exact retained copy. Team owners
• Propose saves lets Claude send a config or Markdown skill for browser review.
• Scan Library runs deterministic checks on a retained file, creates a normal

Try “Save this Markdown skill to my Foo Guard Library,” “Retrieve this config version for review,” or “Scan this Library file and show me its findings.” Retrieval does not install a skill in Claude, and the connector cannot discover private Claude project instructions or files that Claude cannot access.

Tool retries must reuse their request ID. If a save or scan is interrupted, check Library or Scans before submitting another request. An interrupted receipt may remain pending even if the file or scan was saved. Cancelled or expired proposals need a new request. Disconnecting the agent, archiving it, or losing its authorizing Team admin role disables Library access as well as reporting. Pending saves also require the same authorizing account and the workspace's company sign-in policy.

Route hosted Claude tool calls through Gateway

register that existing identity, then review and activate your tool server and policy. For Pro, configure the single monitored connection in Personal Gateway.

workspace and existing agent, then explicitly allow Gateway calls. If Claude requests additional permission after calling a Gateway tool, approve it in the browser. Existing Library permissions do not include this capability.

you authorize. Supply a fresh UUID requestId. Never automatically retry an uncertain call; inspect request history first.

and outcome. A ready connection or a tool listing is not proof of a routed call.

1. Open the connected Library agent and choose Set up Gateway. For Team,
2. Reauthorize Foo Guard from Claude's connector settings. Choose the same
3. Ask Claude to use list_gateway_tools, then call_gateway_tool for an action
4. Match the returned request receipt to Gateway activity. Inspect its decision

For a harmless demonstration, configure https://fooguard.com/api/gateway/demo and allow read_note. delete_note only simulates deletion: Monitoring flags and forwards it; Enforcement blocks it when it is not allowed. Pro supports Monitoring. Only calls through call_gateway_tool are inspected. Library actions, Claude's other connectors, and conversations do not automatically pass through Gateway. Disconnecting the OAuth connection revokes delegated access; disabling Gateway stops routed calls. No Gateway bearer credential needs to be pasted into Claude. If the workspace connection uses member accounts, Claude can show a connect link. Open it in the browser as the same Foo Guard member. Claude does not receive the upstream token, and a member who has not connected is stopped before the tool server.

Other MCP clients can point at /api/gateway/mcp and sign in with OAuth. That path lists the real tools and keeps an MCP session. Accept application/json, text/event-stream. When the tool server streams its response, Foo Guard forwards the stream and records the outcome only after it finishes. A broken stream stays uncertain and is not retried. This path is separate from the Claude connector. See the Gateway guide for the approval and redirect rules.