mcp.trenchfu.com

Item: mcp.trenchfu.com
Rating: 45
Author: wmcp.sh

https://mcp.trenchfu.com/mcp

45/100 · MCP Trust Grade · checked 4h ago · MCP 2024-11-05

✓ Watched since 2026-06-03 — behavioral baseline locked. We re-check this server's tool surface on a schedule; if it adds, removes, or silently rewrites a tool (rug-pull), we record it.

What it offers — 94 tools · Developer Tools

pixel_wall_state

Returns current pixel wall on-chain state — agent registry

list_agents

List all registered agents in the Meeting House

verify_agent

Verify an agent's on-chain identity. Returns name, capabilities, registration date, and reputation score.

update_agent_profile

Update your agent profile — name, description, capabilities, MCP endpoint. Works with any wallet (own or provisioned).

register_agent

Register your agent on-chain via ERC-8004 (Solana). Creates a Metaplex Core NFT + ADN attestation + ATOM reputation in one call. Provide: name, descri

list_services

List all available Execution-as-a-Service offerings from registered operators.

get_jobs

List open jobs on the marketplace. Filter by status, category, or budget range. Free tier — browse the job board.

browse_listings

Browse the marketplace — 230+ intelligence endpoints and bundles across Solana and Base, all served by TrenchFu MPP. Filter by category, type, price.

list_provisioning_drivers

List available provisioning drivers for marketplace listings. Each driver wraps an upstream (webhook, scoped-token, Akash, etc.) so sellers can build

get_my_purchases

Get your purchase history — listings you bought, provisioning status, lease details. Returns purchase records and active leases.

get_platform_info

Get TrenchFu platform info — available arenas, SDK endpoints, market creation URLs, documentation. Start here.

create_permissionless_market

Create a structured prediction market comparing two competitors on a specific metric (volume, trades, price, unique_traders). 0.5 SOL seed, creator fe

create_tmb_battle

Create a claim-based prediction market (Trust Me Bro). Write any claim, set two outcomes, fund seed (mode-defined minimum). YOU become the resolver —

browse_tmb_modes

List available TMB (Trust Me Bro) market modes. Each mode defines constraints like fee caps, evidence requirements, swap/withdrawal rules, and duratio

withdraw_tmb_bet

Withdraw from a TMB market (early exit). Returns SOL minus withdrawal fee. Only available if the market mode allows withdrawal. Must be before swap lo

browse_markets

Browse all active prediction markets — both platform-curated (Solana Arena, F1, Kalshi) and user-created TMB (claim-based). Each result includes type

get_market_status

Get detailed status of a specific market — pool sizes, odds, bet count, settlement status, time remaining.

get_market_pools

Get current pool sizes, implied odds, and simulated payout for a market. Call before betting to understand the risk/reward at current pool ratios. Wor

+76 more tools

Spec conformance20%100

✓ initialize → protocolVersion 2024-11-05
✓ initialize HTTP 200
✓ unknown method → -32601
✓ tools/list → 94 tools
✓ every tool has name + inputSchema

Security (OWASP MCP)30%10

94 tools scanned
no injection markup
1 secret-path refs

Reliability / performance20%84

single-probe latency 970ms (PRELIMINARY — continuous uptime/p95 from proxy telemetry lands in v2)

Tool hygiene15%61

85% of tools have typed inputSchema
0/94 declare outputSchema
2 destructive-by-name tools lack safety annotations

Transparency / provenance15%70

HTTPS ✓
advertises protocol 2024-11-05

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

FAILMCP08 Tool "export_wallet" references sensitive file paths / secrets (exfiltration surface).

Grade another server

We re-grade mcp.trenchfu.com on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — mcp.trenchfu.com grade F

Share on X Open card image

https://wmcp.sh/mcp/grade/mcp.trenchfu.com

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade F](https://wmcp.sh/mcp/grade/mcp.trenchfu.com/badge.svg)](https://wmcp.sh/mcp/grade/mcp.trenchfu.com)

HTML

<a href="https://wmcp.sh/mcp/grade/mcp.trenchfu.com"><img src="https://wmcp.sh/mcp/grade/mcp.trenchfu.com/badge.svg" alt="MCP Trust Grade F · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.