get_attachment_text
Read the text/Markdown content of a file attached to a Workroom thread or sent by a customer (PDF, image, or document). Extracts on first read and caches the result. Returns status "ready" with markdown, or "skipped"/"failed"/"not_found" with a reason. Use when a message references an attachment ...
This record as markdown: /tools/io-favcrm-favcrm/get-attachment-text.md
What get_attachment_text does on FavCRM
AI agents call get_attachment_text to retrieve information from FavCRM without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
attachmentId | string | Yes | The attachment ID from the message attachments list |
Parameters from the server's own tool schema.
Why get_attachment_text is rated Low
This tool performs a pure read operation—it retrieves and extracts text content from attachments without modifying, deleting, or executing anything. The caching mechanism is informational only. The blast radius of misuse is minimal: at worst, an agent could read sensitive customer data already visible in the CRM system, but cannot alter, delete, or trigger external actions.
From the tool's definition Tool description states 'Read the text/Markdown content of a file' and 'Extracts on first read and caches the result.' The verb 'read' and the retrieval-only nature (no modifications, deletions, or side effects) clearly indicate this is a data retrieval…
Attacks that exploit this kind of access
The rule that runs get_attachment_text safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FavCRM, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_attachment_text, this is the rule to start with:
get_attachment_text is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect FavCRM, apply this rule, and every get_attachment_text call is checked against it from then on.
Questions about get_attachment_text
Read the text/Markdown content of a file attached to a Workroom thread or sent by a customer (PDF, image, or document). Extracts on first read and caches the result. Returns status "ready" with markdown, or "skipped"/"failed"/"not_found" with a reason. Use when a message references an attachment you need to read. It is categorised as a Read tool in the FavCRM MCP Server, which means it retrieves data without modifying state.
get_attachment_text accepts 1 parameter: attachmentId. Required: attachmentId. The full parameter table on this page comes from the server's own tool schema.
Register the FavCRM MCP server in PolicyLayer and add a rule for get_attachment_text: 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 FavCRM. Nothing to install.
get_attachment_text 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 get_attachment_text 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 get_attachment_text. 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.
get_attachment_text is provided by the FavCRM MCP server (https://api.favcrm.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FavCRM, and thousands of servers like it.
This server
Across the catalogue