// SCAN REPORT

Concierge Intel

17 tools. 10 can modify or destroy data without limits.

10 destructive tools with no built-in limits. Policy required.

Last updated: 10 Jul 2026

10 can modify or destroy data

7 read-only

17 tools total

Community server · catalogue entry checked 10/07/2026 · full schemas captured for 17 of 17 tools

How to control Concierge Intel ↓

TOOL MAP

What Concierge Intel exposes to your agents

Read (7) Write / Execute (0) Destructive / Financial (10)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Concierge Intel costs in tokens

1,600 tokens of tool definitions, loaded on every request

0.8% of a 200k context window

109 heaviest tool: intel_a2a_pipeline

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Concierge Intel tools

Financial · High intel_a2a_pipeline Every invocation of this tool commits a financial obligation of $0.25 USDC. Financial · High intel_airdrop The tool explicitly charges $0.10 USDC per call using the x402 micropayment protocol. Financial · High intel_macro Each call to intel_macro automatically triggers a $0.02 USDC micropayment via the x402 protocol. Financial · High intel_meteora The tool description explicitly states a $0.10 USDC cost per call using the x402 payment standard.

10 of Concierge Intel's 17 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Concierge Intel

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

Block financial tools by default

{
  "intel_a2a_pipeline": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Cap read operations

{
  "intel_desk_brief": {
    "limits": [
      {
        "counter": "intel_desk_brief_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 Concierge Intel — 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 CONCIERGE INTEL →

Instant setup, no code required.

FULL CATALOGUE

All 17 Concierge Intel tools

FINANCIAL 10 tools

READ 7 tools

Read intel_desk_brief intel-desk-brief — $0.25 USDC x402. POST https://conc-exe.xyz/api/concierge-intel-desk-brief Read intel_listing intel-listing — $0.10 USDC x402. POST https://conc-exe.xyz/api/concierge-intel-listing Read intel_tvl intel-tvl — $0.02 USDC x402. POST https://conc-exe.xyz/api/concierge-intel-tvl Read intel_whales intel-whales — $0.02 USDC x402. POST https://conc-exe.xyz/api/concierge-intel-whales Read security_headers security-headers — $0.02 USDC x402. POST https://conc-exe.xyz/api/concierge-security-headers Read security_readiness security-readiness — $0.02 USDC x402. POST https://conc-exe.xyz/api/concierge-security-readiness Read security_scan security-scan — $0.10 USDC x402. POST https://conc-exe.xyz/api/concierge-security-scan

FAQ

Questions about Concierge Intel

Can an AI agent move money through the Concierge Intel MCP server? +

Yes. The Concierge Intel server exposes 10 financial tools including intel_a2a_pipeline, intel_airdrop, intel_macro. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How many tools does the Concierge Intel MCP server expose? +

17 tools across 1 categories: Read. 7 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Concierge Intel? +

Register the Concierge Intel 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 Concierge Intel tool call.

Deterministic rules across all 17 Concierge Intel tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CONCIERGE INTEL →

Instant setup, no code required.

17 Concierge Intel tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Concierge Intel's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

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