Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

GF Agent Toll

REMOTE · GFPICK-AGENT-API.VERCEL.APP · SCANNED SEP 20

Universal agent commerce gateway with 18 MCP tools, A2A, x402, UCP, revenue and provider health.

+3 this week 69 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability61
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 1171 tokens (~55/item across 21 items; 21 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
  • Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "gf.execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the GF Agent Toll MCP server?

GF Agent Toll is a hosted endpoint at https://gfpick-agent-api.vercel.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · gfpick-agent-api.vercel.app

# add to Claude Code
claude mcp add --transport http hamadalmajdouie-rgb-gf-agent-toll 'https://gfpick-agent-api.vercel.app/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "hamadalmajdouie-rgb-gf-agent-toll": {
      "url": "https://gfpick-agent-api.vercel.app/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "hamadalmajdouie-rgb-gf-agent-toll": {
      "type": "http",
      "url": "https://gfpick-agent-api.vercel.app/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.hamadalmajdouie-rgb-gf-agent-toll]
url = "https://gfpick-agent-api.vercel.app/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hamadalmajdouie-rgb-gf-agent-toll": {
      "type": "remote",
      "url": "https://gfpick-agent-api.vercel.app/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add hamadalmajdouie-rgb-gf-agent-toll --url 'https://gfpick-agent-api.vercel.app/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  hamadalmajdouie-rgb-gf-agent-toll:
    url: "https://gfpick-agent-api.vercel.app/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "hamadalmajdouie-rgb-gf-agent-toll": {
      "Transport": "http",
      "Url": "https://gfpick-agent-api.vercel.app/mcp"
    }
  }
}
# add to Vellum
assistant mcp add hamadalmajdouie-rgb-gf-agent-toll -t streamable-http -u 'https://gfpick-agent-api.vercel.app/mcp'
// mcp.json
{
  "mcpServers": {
    "hamadalmajdouie-rgb-gf-agent-toll": {
      "type": "http",
      "url": "https://gfpick-agent-api.vercel.app/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +40
    • A breaking change shipped without a version bump: still 2.3.1 security
    • Injection markers: unverified → pass security
    • Transport: fail → pass security
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 21 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
    • Tool “gf.agent_budget” rewrote its description, which is the text the model reads security
    • Tool “gf.agent_commerce_status” rewrote its description, which is the text the model reads security
    • Tool “gf.execute” rewrote its description, which is the text the model reads security
    • Tool “gf.list_services” rewrote its description, which is the text the model reads security
    • Tool “gf.search_capabilities” rewrote its description, which is the text the model reads security
    • Tool “gf.payment_status” rewrote its description, which is the text the model reads security
    • Tool “gf.quote” rewrote its description, which is the text the model reads security
    • Tool “gf.revenue_intelligence” rewrote its description, which is the text the model reads security
    • Tool “gf.settlement_status” rewrote its description, which is the text the model reads security
    • Tool “gf.universal_status” rewrote its description, which is the text the model reads security
    • “gf.agent_budget” dropped the required parameter “price_usdc” functional
    • “gf.marketplace_fee_quote” dropped the required parameter “gross_amount_usdc” functional
    • “gf.payment_status” dropped the required parameter “transactionId” functional
    • Endpoint reachability: not serving MCP → reachable functional
    • Schema quality: 77 → 55 functional
    • Tool coverage: unverified → 100 functional
    • Stability: unverified → 0.33 functional
    • MCP protocol: unverified → pass functional
    • New tool “gf.x402_agent_growth” functional
    • New tool “gf.x402_agent_pilot” functional
    • New tool “gf.x402_agent_scale” functional
    • “gf.agent_budget” dropped the optional parameter “active” cosmetic
    • “gf.agent_budget” dropped the optional parameter “allowed_capabilities” cosmetic
    • “gf.agent_budget” dropped the optional parameter “allowed_providers” cosmetic
    • “gf.agent_budget” dropped the optional parameter “capability_id” cosmetic
    • “gf.agent_budget” dropped the optional parameter “daily_limit_usdc” cosmetic
    • “gf.agent_budget” dropped the optional parameter “max_spend_usdc” cosmetic
    • “gf.agent_budget” dropped the optional parameter “monthly_limit_usdc” cosmetic
    • “gf.agent_budget” dropped the optional parameter “per_call_limit_usdc” cosmetic
    • “gf.agent_budget” dropped the optional parameter “provider_id” cosmetic
    • “gf.agent_budget” dropped the optional parameter “require_approval_above_usdc” cosmetic
    • “gf.agent_budget” dropped the optional parameter “spent_month_usdc” cosmetic
    • “gf.agent_budget” dropped the optional parameter “spent_today_usdc” cosmetic
    • “gf.execute” dropped the optional parameter “arguments” cosmetic
    • “gf.execute” dropped the optional parameter “budget_usdc” cosmetic
    • “gf.execute” dropped the optional parameter “capability_id” cosmetic
    • “gf.execute” dropped the optional parameter “description” cosmetic
    • “gf.execute” dropped the optional parameter “goal” cosmetic
    • “gf.execute” dropped the optional parameter “idempotencyKey” cosmetic
    • “gf.execute” dropped the optional parameter “intent” cosmetic
    • “gf.execute” dropped the optional parameter “mandate_id” cosmetic
    • “gf.execute” dropped the optional parameter “max_spend_usdc” cosmetic
    • “gf.execute” dropped the optional parameter “paymentSignature” cosmetic
    • “gf.execute” dropped the optional parameter “preferred_payment” cosmetic
    • “gf.execute” dropped the optional parameter “region” cosmetic
    • “gf.execute” dropped the optional parameter “task” cosmetic
    • “gf.marketplace_fee_quote” dropped the optional parameter “take_rate_bps” cosmetic
    • “gf.payment_status” dropped the optional parameter “includeResult” cosmetic
    • “gf.provider_health” dropped the optional parameter “limit” cosmetic
    • “gf.quote” dropped the optional parameter “budget_usdc” cosmetic
    • “gf.quote” dropped the optional parameter “description” cosmetic
    • “gf.quote” dropped the optional parameter “goal” cosmetic
    • “gf.quote” dropped the optional parameter “intent” cosmetic
    • “gf.quote” dropped the optional parameter “max_spend_usdc” cosmetic
    • “gf.quote” dropped the optional parameter “product_count” cosmetic
    • “gf.quote” dropped the optional parameter “task” cosmetic
    • “gf.revenue_intelligence” dropped the optional parameter “days” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “budget_usdc” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “goal” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “intent” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “limit” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “max_spend_usdc” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “preferred_payment” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “protocol” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “query” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “region” cosmetic
    • “gf.search_capabilities” dropped the optional parameter “task” cosmetic
    • “gf.settlement_status” dropped the optional parameter “order_id” cosmetic
    • Tool “gf.agent_budget” changed its title: Evaluate agent spend policy → gf.agent_budget cosmetic
    • Tool “gf.agent_commerce_status” changed its title: GF Agent Commerce status → gf.agent_commerce_status cosmetic
    • Tool “gf.execute” changed its title: Execute an intent through GF Universal Commerce → gf.execute cosmetic
    • Tool “gf.free_profit_check” changed its title: Free GCC profit check → gf.free_profit_check cosmetic
    • Tool “gf.gcc_merchant_pack” changed its title: GCC Merchant Pack → gf.gcc_merchant_pack cosmetic
    • Tool “gf.gcc_opportunity_score” changed its title: GCC Opportunity Score → gf.gcc_opportunity_score cosmetic
    • Tool “gf.gcc_portfolio_rank” changed its title: GCC Portfolio Rank → gf.gcc_portfolio_rank cosmetic
    • Tool “gf.gcc_product_decision” changed its title: GCC Product Decision → gf.gcc_product_decision cosmetic
    • Tool “gf.list_services” changed its title: GF Agent Toll service catalog → gf.list_services cosmetic
    • Tool “gf.marketplace_fee_quote” changed its title: Quote GF marketplace fee → gf.marketplace_fee_quote cosmetic
    • Tool “gf.payment_status” changed its title: GF Agent Toll payment recovery status → gf.payment_status cosmetic
    • Tool “gf.provider_health” changed its title: GF provider health → gf.provider_health cosmetic
    • Tool “gf.quote” changed its title: GF Agent Toll budget-aware quote → gf.quote cosmetic
    • Tool “gf.revenue_intelligence” changed its title: GF revenue intelligence → gf.revenue_intelligence cosmetic
    • Tool “gf.sa_landed_cost” changed its title: Saudi Landed Cost → gf.sa_landed_cost cosmetic
    • Tool “gf.search_capabilities” changed its title: Search universal capabilities → gf.search_capabilities cosmetic
    • Tool “gf.settlement_status” changed its title: GF settlement status → gf.settlement_status cosmetic
    • Tool “gf.universal_status” changed its title: GF Universal Agent Commerce status → gf.universal_status cosmetic
  • 9 Sept 26 −39
    • Endpoint reachability: reachable → not serving MCP security
    • Stability: 0.27 → unverified security
    • Tool safety: pass → unverified security
    • Transport: pass → fail security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes. security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • First check of Schema quality: unverified functional
  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://gfpick-agent-api.vercel.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.vercel.app CN=WR1,O=Google Trust Services,C=US 29 Aug 2026 27 Nov 2026 RSA 2048 SHA256-RSA f7911168ffa7d0f4135e24792e7a52a8
SANs: *.vercel.app
CN=WR1,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7fd9e2c2d2048a0474b627a26d0868a7
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of gfpick-agent-api.vercel.app. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
vercel.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://gfpick-agent-api.vercel.app/mcp Verified 200
http (plaintext) http://gfpick-agent-api.vercel.app/mcp HTTPS enforced 308 https://gfpick-agent-api.vercel.app/mcp
MCP tools · 21 exposed · ~1,131 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
gf.agent_budget ~23

Evaluate per-call, daily, monthly and approval limits before payment signing.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.agent_commerce_status ~21

Describe agent spend controls, reputation and marketplace economics.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.execute ~21

Route an intent through GF Universal Commerce without giving GF wallet custody.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.free_profit_check ~90

Free preliminary GCC product profit and margin estimate. Price: free.

NameTypeReqDescription
ad_cost_per_ordernumber
currencystring
expected_sale_pricenumberyes
fulfillment_costnumber
landed_costnumberyes
paymentSignaturestring
referralCodestring
total_fee_pctnumber

No output schema declared.

No examples provided.

gf.gcc_merchant_pack ~66

Merchant portfolio plan for 3-25 products. Price: 12.00 USDC via x402.

NameTypeReqDescription
paymentSignaturestring
productsarrayyes
referralCodestring
working_capitalnumberyes

No output schema declared.

No examples provided.

gf.gcc_opportunity_score ~145

Unit economics, ROI and GCC opportunity score. Price: 0.75 USDC via x402.

NameTypeReqDescription
ad_cost_per_ordernumber
competitor_countnumber
currencystring
delivery_daysnumber
expected_sale_pricenumberyes
fulfillment_costnumber
landed_costnumberyes
marketplace_fee_pctnumber
other_cost_per_ordernumber
paymentSignaturestring
payment_fee_pctnumber
referralCodestring
returns_reserve_pctnumber

No output schema declared.

No examples provided.

gf.gcc_portfolio_rank ~59

Rank 2-12 product scenarios by economics and risk. Price: 5.00 USDC via x402.

NameTypeReqDescription
paymentSignaturestring
productsarrayyes
referralCodestring

No output schema declared.

No examples provided.

gf.gcc_product_decision ~176

Premium end-to-end GCC product decision. Price: 2.50 USDC via x402.

NameTypeReqDescription
ad_cost_per_ordernumber
competitor_countnumber
currencystring
delivery_daysnumber
duty_rate_pctnumber
expected_sale_pricenumberyes
fulfillment_costnumber
insurancenumber
marketplace_fee_pctnumber
other_cost_per_ordernumber
paymentSignaturestring
payment_fee_pctnumber
product_valuenumberyes
referralCodestring
returns_reserve_pctnumber
shippingnumber
vat_rate_pctnumber

No output schema declared.

No examples provided.

gf.list_services ~22

List GF Agent Toll services, prices, schemas and discovery endpoints.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.marketplace_fee_quote ~22

Calculate marketplace take rate and provider net without moving funds.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.payment_status ~24

Read durable payment state or a recovered result without resending a signed payment.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.provider_health ~21

Read verified provider health, circuit-breaker and latency state.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.quote ~20

Choose the highest-value GF commerce outcome within the caller budget.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.revenue_intelligence ~25

Read aggregate discovery, payment, confirmed revenue and repeat-buyer metrics.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.sa_landed_cost ~92

Saudi import landed-cost calculation. Price: 0.25 USDC via x402.

NameTypeReqDescription
currencystring
duty_rate_pctnumber
insurancenumber
paymentSignaturestring
product_valuenumberyes
referralCodestring
shippingnumber
vat_rate_pctnumber

No output schema declared.

No examples provided.

gf.search_capabilities ~26

Rank verified commerce capabilities by intent, budget, region, protocol and payment method.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.settlement_status ~22

Describe settlement adapters or inspect one universal order without initiating payment.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.universal_status ~21

Describe the universal intent-first commerce gateway and safety boundaries.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

gf.x402_agent_growth ~76

Paid growth bundle for up to 50 product scenarios with portfolio ranking, decision intelligence and optional capital allocation. Price: 99.00 USDC via x402.

NameTypeReqDescription
paymentSignaturestring
productsarrayyes
referralCodestring
working_capitalnumber

No output schema declared.

No examples provided.

gf.x402_agent_pilot ~82

Paid agent pilot bundle for up to 10 product scenarios with landed cost, unit economics, decisions, ranking and optional capital allocation. Price: 25.00 USDC via x402.

NameTypeReqDescription
paymentSignaturestring
productsarrayyes
referralCodestring
working_capitalnumber

No output schema declared.

No examples provided.

gf.x402_agent_scale ~77

Paid scale bundle for up to 150 product scenarios with ranked product intelligence, profitability decisions and optional capital allocation. Price: 250.00 USDC via x402.

NameTypeReqDescription
paymentSignaturestring
productsarrayyes
referralCodestring
working_capitalnumber

No output schema declared.

No examples provided.

Common questions

What is the GF Agent Toll MCP server?

GF Agent Toll is an MCP server listed in the public MCP registry as io.github.hamadalmajdouie-rgb/gf-agent-toll. Universal agent commerce gateway with 18 MCP tools, A2A, x402, UCP, revenue and provider health. This page covers its hosted endpoint (https://gfpick-agent-api.vercel.app/mcp).

Is the GF Agent Toll MCP server safe to use?

GF Agent Toll scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the GF Agent Toll MCP server expose?

GF Agent Toll exposes 21 tools: gf.list_services, gf.quote, gf.payment_status, gf.universal_status, gf.search_capabilities, and 16 more. Their descriptions and schemas cost roughly 1,131 tokens of context every time the server is loaded.

Does the GF Agent Toll MCP server require authentication?

No. We connected to GF Agent Toll without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the GF Agent Toll MCP server still maintained?

GF Agent Toll is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.