# create_oauth_credential

Create an OAuth credential that actions can reference by name to get a fresh access token at invoke time (injected as ${OAUTH_ACCESS_TOKEN}). Walk the user through: (1) which upstream API, (2) which grant type fits (client_credentials for M2M like Auth0/Okta; password for FreeWheel/legacy; jwt_bearer for Google Cloud). For Google, prefer google_service_account_json — ask them to paste the whole JSON. Do NOT echo client_secret, password, or private keys back to the user after they

Agent View of the PolicyLayer registry record for `create_oauth_credential`. HTML page: https://policylayer.com/tools/deloc-mcp/create-oauth-credential

## Facts

- Tool: `create_oauth_credential`
- Server: Deloc (`delocdev/deloc-mcp`) — https://policylayer.com/tools/deloc-mcp.md
- Homepage: https://github.com/delocdev/deloc-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_oauth_credential",
    "arguments": {}
  }
}
```

## Why create_oauth_credential is rated Medium

This tool creates and stores credentials used for authentication, which is a Write operation that modifies system state by adding new OAuth credentials. While it doesn't directly execute code or delete data, the high severity reflects that misconfigured or compromised credentials could be abused to access upstream APIs with side effects.

From the tool's own definition: "Tool creates OAuth credentials that are stored and referenced by actions ('Create an OAuth credential that actions can reference by name')."

## Use case

AI agents use create_oauth_credential to create or update resources in Deloc, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Deloc environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Deloc:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_oauth_credential": {
      "limits": [
        {
          "counter": "create_oauth_credential_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Deloc (44)

- `delete_action` — Destructive — https://policylayer.com/tools/deloc-mcp/delete-action.md
- `delete_action_secret` — Destructive — https://policylayer.com/tools/deloc-mcp/delete-action-secret.md
- `delete_app` — Destructive — https://policylayer.com/tools/deloc-mcp/delete-app.md
- `delete_dashboard_query` — Destructive — https://policylayer.com/tools/deloc-mcp/delete-dashboard-query.md
- `delete_data_connection` — Destructive — https://policylayer.com/tools/deloc-mcp/delete-data-connection.md
- `delete_oauth_credential` — Destructive — https://policylayer.com/tools/deloc-mcp/delete-oauth-credential.md
- `disable_app` — Destructive — https://policylayer.com/tools/deloc-mcp/disable-app.md
- `logout` — Destructive — https://policylayer.com/tools/deloc-mcp/logout.md
- `deploy` — Execute — https://policylayer.com/tools/deloc-mcp/deploy.md
- `run_dashboard_query` — Execute — https://policylayer.com/tools/deloc-mcp/run-dashboard-query.md
- `test_action` — Execute — https://policylayer.com/tools/deloc-mcp/test-action.md
- `test_oauth_credential` — Execute — https://policylayer.com/tools/deloc-mcp/test-oauth-credential.md
- `bigquery_get_table_schema` — Read — https://policylayer.com/tools/deloc-mcp/bigquery-get-table-schema.md
- `bigquery_list_datasets` — Read — https://policylayer.com/tools/deloc-mcp/bigquery-list-datasets.md
- `bigquery_list_projects` — Read — https://policylayer.com/tools/deloc-mcp/bigquery-list-projects.md
- `bigquery_list_tables` — Read — https://policylayer.com/tools/deloc-mcp/bigquery-list-tables.md
- `check_bigquery_connection` — Read — https://policylayer.com/tools/deloc-mcp/check-bigquery-connection.md
- `get_account` — Read — https://policylayer.com/tools/deloc-mcp/get-account.md
- `get_action_logs` — Read — https://policylayer.com/tools/deloc-mcp/get-action-logs.md
- `get_app` — Read — https://policylayer.com/tools/deloc-mcp/get-app.md
- `list_action_secrets` — Read — https://policylayer.com/tools/deloc-mcp/list-action-secrets.md
- `list_actions` — Read — https://policylayer.com/tools/deloc-mcp/list-actions.md
- `list_apps` — Read — https://policylayer.com/tools/deloc-mcp/list-apps.md
- `list_dashboard_queries` — Read — https://policylayer.com/tools/deloc-mcp/list-dashboard-queries.md
- `list_data_connections` — Read — https://policylayer.com/tools/deloc-mcp/list-data-connections.md
- `list_data_files` — Read — https://policylayer.com/tools/deloc-mcp/list-data-files.md
- `list_oauth_credentials` — Read — https://policylayer.com/tools/deloc-mcp/list-oauth-credentials.md
- `suggest_deploy_options` — Read — https://policylayer.com/tools/deloc-mcp/suggest-deploy-options.md
- `connect_bigquery` — Write — https://policylayer.com/tools/deloc-mcp/connect-bigquery.md
- `create_action` — Write — https://policylayer.com/tools/deloc-mcp/create-action.md
- …and 14 more: https://policylayer.com/tools/deloc-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=deloc-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deloc-mcp