// SCAN REPORT

Enterprise AI Bridge (MCP)

9 tools. 4 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

4 can modify or destroy data

5 read-only

9 tools total

Community server · catalogue entry verified 03/07/2026

How to control Enterprise AI Bridge (MCP) ↓

TOOL MAP

What Enterprise AI Bridge (MCP) exposes to your agents

Read (5) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Enterprise AI Bridge (MCP) tools

Destructive · High delete_jira_issue Deletion of Jira issues is an irreversible action that cannot be undone through normal means. Write · Medium add_ai_research_summary_to_issue_comment This tool performs a Write operation: it creates new comment data on a Jira issue by composing AI-generated research and appending it. Write · Medium assign_jira_issue Assigning an issue to a user modifies project data reversibly. Write · Medium create_jira_issue The tool creates new Jira issues, which is a Write operation (creates data reversibly).

4 of Enterprise AI Bridge (MCP)'s 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Enterprise AI Bridge (MCP)

PolicyLayer is an MCP gateway — it sits between your AI agents and Enterprise AI Bridge (MCP), and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_jira_issue": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_ai_research_summary_to_issue_comment": {
    "limits": [
      {
        "counter": "add_ai_research_summary_to_issue_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_all_jira_issues": {
    "limits": [
      {
        "counter": "get_all_jira_issues_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Enterprise AI Bridge (MCP) — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ENTERPRISE AI BRIDGE (MCP) →

Instant setup, no code required.

FULL CATALOGUE

All 9 Enterprise AI Bridge (MCP) tools

DESTRUCTIVE 1 tools

Destructive delete_jira_issue Deletes a Jira issue by its key (e.g., 'KAN-7').

WRITE 3 tools

Write add_ai_research_summary_to_issue_comment Researches a technical solution and adds it to a Jira issue. Write assign_jira_issue Assign a Jira issue by its key (e.g., 'KAN-7') and account id. Write create_jira_issue Creates a new Jira task.

READ 5 tools

Read get_all_jira_issues Returns a list of all issues for a given project key (e.g., 'KAN'). Read get_jira_context Returns available Jira projects and keys. Read list_jira_issues Lists Jira tasks assigned to the current user that are not yet completed. Read search_emails Searches Office 365 inbox using KQL. Read search_gmail_emails Searches gmail inbox using a search query query.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Enterprise AI Bridge (MCP)

Can an AI agent delete data through the Enterprise AI Bridge (MCP) MCP server? +

Yes. The Enterprise AI Bridge (MCP) server exposes 1 destructive tools including delete_jira_issue. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Enterprise AI Bridge (MCP)? +

The Enterprise AI Bridge (MCP) server has 3 write tools including add_ai_research_summary_to_issue_comment, assign_jira_issue, create_jira_issue. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Enterprise AI Bridge (MCP).

How many tools does the Enterprise AI Bridge (MCP) MCP server expose? +

9 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Enterprise AI Bridge (MCP)? +

Register the Enterprise AI Bridge (MCP) MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Enterprise AI Bridge (MCP) tool call.

Deterministic rules across all 9 Enterprise AI Bridge (MCP) tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ENTERPRISE AI BRIDGE (MCP) →

Instant setup, no code required.

9 Enterprise AI Bridge (MCP) tools catalogued and risk-classified — across an index of 43,000+ MCP servers.