// SCAN REPORT

Forge Treasury

9 tools. 3 can modify or destroy data without limits.

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

Last updated: 17 Aug 2026

3 can modify or destroy data

6 read-only

9 tools total

Community server · catalogue entry checked 17/08/2026 · full schemas captured for 7 of 9 tools

How to control Forge Treasury ↓

TOOL MAP

What Forge Treasury exposes to your agents

Read (6) Write / Execute (0) Destructive / Financial (3)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Forge Treasury costs in tokens

1,048 tokens of tool definitions, loaded on every request

0.5% of a 200k context window

222 heaviest tool: deposit

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

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Forge Treasury tools

Financial · Critical deposit This tool directly moves USDC (a stablecoin representing real financial value) from an agent's wallet into a yield vault on Base mainnet. Financial · Critical withdraw This tool directly moves money (USDC withdrawals from a yield vault) and applies financial fees. Financial · High claim_forge This tool builds and potentially submits calldata to claim $FORGE token rewards on Base mainnet.

3 of Forge Treasury'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 Forge Treasury

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

Block financial tools by default

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

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

Cap read operations

{
  "get_balance": {
    "limits": [
      {
        "counter": "get_balance_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 Forge Treasury — 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 FORGE TREASURY →

Instant setup, no code required.

FULL CATALOGUE

All 9 Forge Treasury tools

FINANCIAL 3 tools

Financial claim_forge [Advanced] Build calldata to claim weekly $FORGE rewards. Proof is fetched from forgetreasury.com/rewards when Financial deposit Deposit USDC into a Forge Treasury vault on Base. Returns calldata for the agent wallet to sign. The agent mus Financial withdraw Withdraw from the Forge Treasury vault by redeeming shares. Returns calldata for the agent wallet. A 15% perfo

READ 6 tools

Read get_balance Get an agent's Forge vault balance: shares held and equivalent USDC value. Read-only, no transaction needed. Read get_current_apy Get the blended target APY for a Forge profile: base USDC yield + FORGE boost. Returns structured JSON with pr Read get_forge_rewards [Advanced] Get claimable $FORGE reward balance for an agent from the weekly emissions distributor. Read get_vault_stats Get live Forge vault TVL on Base (conservative profile in MVP). Read-only. Read list_profiles List Forge vaults (Core/Middle/Infra) and agent strategies (Conservative/Balanced/Aggressive). Mainnet: Core a Read simulate_deposit Project expected returns for a USDC deposit over 30, 90, and 365 days using the blended target APY. Use for ag

EXPLORE

Related servers

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

FAQ

Questions about Forge Treasury

Can an AI agent move money through the Forge Treasury MCP server? +

Yes. The Forge Treasury server exposes 3 financial tools including claim_forge, deposit, withdraw. 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 Forge Treasury MCP server expose? +

9 tools across 3 categories: Execute, Financial, Read. 6 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Forge Treasury? +

Register the Forge Treasury 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 Forge Treasury tool call.

Deterministic rules across all 9 Forge Treasury tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FORGE TREASURY →

Instant setup, no code required.

9 Forge Treasury tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Forge Treasury'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 →