Read one indexed brand document. Returns the indexed metadata (doc_type, summary, key_topics, entities, key_quotes) plus the document content, routed by mime: text/markdown, text/plain, text/csv are inlined as text; application/pdf and other text-shaped mimes return an Anthropic Files API file_id...
Part of the Heista server.
Free to start. No card required.
AI agents call read_brand_document to retrieve information from Heista 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 read_brand_document 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.
{
"version": "1",
"default": "deny",
"tools": {
"read_brand_document": {}
}
}See the full Heista policy for all 69 tools.
These attack patterns abuse exactly the kind of access read_brand_document gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Read one indexed brand document. Returns the indexed metadata (doc_type, summary, key_topics, entities, key_quotes) plus the document content, routed by mime: text/markdown, text/plain, text/csv are inlined as text; application/pdf and other text-shaped mimes return an Anthropic Files API file_id (attach via document source { type:"file", file_id } on the next turn); DOCX/PPTX/XLSX return a requires_code_execution marker (caller must enable code_execution_20260120 and attach via container_upload). Use AFTER list_brand_documents to pick the right document. Free, read-only.. It is categorised as a Read tool in the Heista MCP Server, which means it retrieves data without modifying state.
Register the Heista MCP server in PolicyLayer and add a rule for read_brand_document: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Heista. Nothing to install.
read_brand_document 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 read_brand_document rule in your PolicyLayer 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 PolicyLayer policy for read_brand_document. 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.
read_brand_document is provided by the Heista MCP server (https://www.heista.co/api/mcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 69 Heista tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.