crm_connector

SERVERMcp Knowledge SOURCEhttps://mcp.gapup.io

Medium RISK CLASS

Category Write

Parameters 53 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-getgapup-mcp-knowledge/crm-connector.md

WHAT IT DOES

What crm_connector does on Mcp Knowledge

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

Parameter	Type	Required	Description
`data`	object	Yes	Payload depending on mode. push_lead: {email,first_name,last_name,company,phone,job_title}. update_opportunity: {deal_id/opportunity_id,stage,amount,close_date}
`mode`	string	Yes	Action to perform in the CRM
`async`	boolean	—	If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti
`provider`	string	Yes	CRM provider to target
`credentials`	object	—	Auth credentials. HubSpot: access_token. Salesforce: access_token + base_url. Pipedrive: api_key.

Parameters from the server's own tool schema.

RISK

Why crm_connector is rated Medium

The tool's primary functions are Write operations: creating new contacts/leads, updating deal stages and amounts, and logging activities. These are all reversible data modifications in production CRM systems. While search_contact is Read, the tool's capability to create and update takes precedence. The tool requires live CRM credentials and returns direct CRM URLs, confirming it operates against real systems.

From the tool's definition Tool performs 'push_lead' (create contact/lead), 'update_opportunity' (update deal stage/amount), 'search_contact' (lookup), and 'log_activity' (call/email/meeting/note).

Risk signalsAccepts URL/endpoint input (credentials.base_url) · Handles credentials or secrets (credentials)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs crm_connector safely

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

crm_connector Rate-limited

crm_connector 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": {
    "crm_connector": {
      "limits": [
        {
          "counter": "crm_connector_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 Mcp Knowledge, apply this rule, and every crm_connector call is checked against it from then on.

FAQ

Questions about crm_connector

What does the crm_connector tool do? +

Push, update, search and log activities in HubSpot, Salesforce or Pipedrive. 4 modes: push_lead (create contact/lead), update_opportunity (update deal stage/amount), search_contact (lookup by email), log_activity (call/email/meeting/note). Returns resource_id, direct CRM URL, signals and quality_score. If credentials are absent, returns a mock result with a warning signal. Auth: HubSpot via Bearer access_token; Salesforce via access_token + base_url; Pipedrive via api_key. It is categorised as a Write tool in the Mcp Knowledge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does crm_connector accept? +

crm_connector accepts 5 parameters: data, mode, async, provider, credentials. Required: data, mode, provider. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on crm_connector? +

Register the Mcp Knowledge MCP server in PolicyLayer and add a rule for crm_connector: 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 Mcp Knowledge. Nothing to install.

What risk level is crm_connector? +

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

Can I rate-limit crm_connector? +

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

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

crm_connector is provided by the Mcp Knowledge MCP server (https://mcp.gapup.io). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Knowledge, and thousands of servers like it.

This server

All 271 Mcp Knowledge tools →

Across the catalogue

The MCP Attack Database →

Guides

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