add_knowledge_text

Add a free-form text document to the knowledge base. Use for pasted policies, FAQs, internal notes, brand voice references — anything the agent should be able to retrieve later. Stored as a single document; agent-side embedding/retrieval happens elsewhere.

SERVERFavCRM SOURCEhttps://api.favcrm.io/mcp
Medium RISK CLASS
Category Write
Parameters 22 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-favcrm-favcrm/add-knowledge-text.md

What add_knowledge_text does on FavCRM

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

ParameterTypeRequiredDescription
name string Yes Friendly title for the document
content string Yes Document body text

Parameters from the server's own tool schema.

Why add_knowledge_text is rated Medium

This tool creates or stores new data (a text document) in a knowledge base, which is a reversible write operation. There are no destructive effects (deletion/overwriting), no code execution, and no financial transactions. The blast radius is low — an agent adding unwanted or incorrect text to the knowledge base is recoverable by editing or deleting that document later.

From the tool's definition "Add a free-form text document to the knowledge base" — creates and stores new text data in a knowledge base without destructive or financial implications.

Risk signalsAccepts raw HTML/template content (content)

Questions about add_knowledge_text

What does the add_knowledge_text tool do? +

Add a free-form text document to the knowledge base. Use for pasted policies, FAQs, internal notes, brand voice references — anything the agent should be able to retrieve later. Stored as a single document; agent-side embedding/retrieval happens elsewhere. It is categorised as a Write tool in the FavCRM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does add_knowledge_text accept? +

add_knowledge_text accepts 2 parameters: name, content. Required: name, content. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on add_knowledge_text? +

Register the FavCRM MCP server in PolicyLayer and add a rule for add_knowledge_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.

What risk level is add_knowledge_text? +

add_knowledge_text is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_knowledge_text? +

Yes. Add a rate_limit block to the add_knowledge_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.

How do I block add_knowledge_text completely? +

Set action: deny in the PolicyLayer policy for add_knowledge_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.

What MCP server provides add_knowledge_text? +

add_knowledge_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.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of FavCRM's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.