Make an API request with stored credentials. The API key is injected automatically — the bot never sees it. Supports header, query param, and basic auth patterns.
Accepts URL/endpoint input (url); Accepts raw HTML/template content (body)
Part of the Vault MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call vault_api_request to retrieve information from Vault MCP without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though vault_api_request only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
vault_api_request:
rules:
- action: allowSee the full Vault MCP policy for all 10 tools.
Agents calling read-class tools like vault_api_request have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Make an API request with stored credentials. The API key is injected automatically — the bot never sees it. Supports header, query param, and basic auth patterns.. It is categorised as a Read tool in the Vault MCP MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for vault_api_request. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Vault MCP MCP server.
vault_api_request is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the vault_api_request rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for vault_api_request. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
vault_api_request is provided by the Vault MCP MCP server (chillai-vault-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept