Medium Risk

contacts-create_research

Start asynchronous AI research for a contact using LinkedIn and other sources, then poll the research ID for results.

Part of the Saber server.

contacts-create_research can modify Saber data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE SABER →

Free to start. No card required.

AI agents use contacts-create_research to create or modify resources in Saber. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call contacts-create_research repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Saber.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "contacts-create_research": {
      "limits": [
        {
          "counter": "contacts-create_research_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Saber policy for all 77 tools.

Get this rule live on your own Saber server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY SABER →

View all 77 tools →

These attack patterns abuse exactly the kind of access contacts-create_research gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so contacts-create_research only ever does what you allow.

SECURE SABER →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the contacts-create_research tool do? +

Start asynchronous AI research for a contact using LinkedIn and other sources, then poll the research ID for results.. It is categorised as a Write tool in the Saber MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on contacts-create_research? +

Register the Saber MCP server in PolicyLayer and add a rule for contacts-create_research: 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 Saber. Nothing to install.

What risk level is contacts-create_research? +

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

Can I rate-limit contacts-create_research? +

Yes. Add a rate_limit block to the contacts-create_research 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 contacts-create_research completely? +

Set action: deny in the PolicyLayer policy for contacts-create_research. 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 contacts-create_research? +

contacts-create_research is provided by the Saber MCP server (https://mcp.saber.app/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Saber tool call.

Deterministic rules across all 77 Saber 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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.