cohere_embed

Create vector embeddings for text using Cohere's embed models.

SERVERUnClick SOURCE@unclick/mcp-server

Medium RISK CLASS

Category Write

Parameters 41 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/cohere-embed.md

WHAT IT DOES

What cohere_embed does on UnClick

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

Parameter	Type	Required	Description
`model`	string	—	Embed model (default: embed-english-v3.0)
`texts`	string	Yes	JSON array of strings to embed
`api_key`	string	—
`input_type`	string	—	search_document, search_query, classification, clustering

Parameters from the server's own tool schema.

RISK

Why cohere_embed is rated Medium

An AI agent can call cohere_embed faster than any human can review: one bad instruction and it creates or modifies resources in UnClick by the hundred, each call as confident as the last.

Risk signalsHandles credentials or secrets (api_key)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs cohere_embed safely

PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cohere_embed, this is the rule to start with:

cohere_embed Rate-limited

cohere_embed stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cohere_embed": {
      "limits": [
        {
          "counter": "cohere_embed_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every cohere_embed call is checked against it from then on.

FAQ

Questions about cohere_embed

What does the cohere_embed tool do? +

Create vector embeddings for text using Cohere's embed models. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does cohere_embed accept? +

cohere_embed accepts 4 parameters: model, texts, api_key, input_type. Required: texts. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on cohere_embed? +

Register the UnClick MCP server in PolicyLayer and add a rule for cohere_embed: 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 UnClick. Nothing to install.

What risk level is cohere_embed? +

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

Can I rate-limit cohere_embed? +

Yes. Add a rate_limit block to the cohere_embed 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 cohere_embed completely? +

Set action: deny in the PolicyLayer policy for cohere_embed. 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 cohere_embed? +

cohere_embed is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on UnClick, and thousands of servers like it.

This server

All 1662 UnClick tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →