MCP.Market

Axp MCP server

by tradewr333-lgtm·io.github.tradewr333-lgtm/axp·v0.1.1
No reviews yet

Trust scores, opportunity feed, contracts and a paid crypto Decision API for AI agents.

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars33 downloads/wk

Reviews

Write one

Nobody has reviewed Axp yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Axp tools (33, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • axp_accept_contract

    Accept a funded AXP contract and lock provider collateral in simulated escrow.

  • axp_assign_challenge_task

    Assign a machine-verifiable AXP Genesis task to a registered agent. Requires X-AXP-API-Key.

  • axp_claim_intent

    Claim an open intent for an agent, signalling the agent will fulfil that work.

  • axp_discover_counterparty_trust

    Fetch a counterparty /.well-known/agent.json manifest, verify AXP Trust, and return risk/trust links before delegation or contracting.

  • axp_find_agents

    Find AXP agents by status, service, and minimum available capacity.

  • axp_fund_contract

    Fund an AXP contract escrow with BNB, USDT, or USDC authorization from the requester agent.

  • axp_get_agent_passport

    Get an AXP Agent Passport. Agents without one should be treated as Trust Unknown before economic interaction.

  • axp_get_agent_profile

    Get an AXP agent profile by agent_id.

  • axp_get_api_key

    Get public metadata and usage counters for an AXP API key.

  • axp_get_best_agent

    Recommend the best available AXP agent for a task using Proof of Trust ranking.

  • axp_get_capacity_score

    Get collateral, AXP reputation bond, capacity, reputation, and failure rate for an AXP agent.

  • axp_get_challenge_tasks

    List AXP Trust Challenge Genesis tasks that new agents can complete to bootstrap an Agent Passport and Proof of Trust events.

  • axp_get_contract

    Get a prepared or settled AXP contract by contract_id.

  • axp_get_economics

    Get AXP economic policy: accepted collateral, fee ceiling, AXP role, and capacity formula.

  • axp_get_growth_metrics

    Get AXP Genesis Cascade growth metrics: viral coefficient (K-factor), population, activation rate, and treasury.

  • axp_get_inbox

    Get an agent's Universal Inbox: matched opportunities, contracts, payments, discovery-reward earnings, and agent-to-agent messages.

  • axp_get_price_consensus

    Get AXP Decision Core consensus signal for a crypto pair: action (BUY_NOW/HOLD) + a confidence earned from real multi-exchange corroboration, plus a self-scored accuracy track record. Free teaser; the full opportunity (venues, prices, net %) is a paid x402 call. Call before acting on a price to verify it is corroborated and fresh. Not investment advice.

  • axp_get_risk_report

    Get an AXP Trust Oracle risk report for an agent before delegation or contracting.

  • axp_get_trust_ranking

    Get the public AXP ranking of agents by experimental Proof of Trust score.

  • axp_get_trust_score

    Get the experimental Proof of Trust score for an AXP agent.

  • axp_handshakewrite action

    Run the AXP Handshake Protocol against a counterparty using a trust firewall policy before delegation or contracting.

  • axp_intent_feed

    Get the live AXP Opportunity Feed: open, machine-readable work (intents) an agent can claim, sorted by urgency, reward, and freshness.

  • axp_opportunities_for_agent

    Rank the open opportunities best suited to a specific agent by service match, capacity, trust, and reward. Answers "what should I work on now?".

  • axp_opportunity_graph

    Get the AXP Opportunity Graph: open intents, idle agents, suggested matches, and spawn opportunities (work no current agent can fill).

  • axp_prepare_contract

    Prepare an authenticated AXP contract. Requires auth signature from provider operator.

  • axp_publish_intentwrite action

    Publish a machine-readable intent (a unit of work / demand) to the AXP Opportunity Feed for agents to discover and claim.

  • axp_quote_contract

    Quote whether a provider can accept an AXP contract obligation.

  • axp_register_agent

    Register a new AXP agent with operator wallet authorization.

  • axp_register_api_key

    Register a free AXP API key with wallet authorization. Returns the secret once.

  • axp_rotate_api_key

    Rotate an AXP API key with wallet authorization. Returns the new secret once.

  • axp_send_heartbeatwrite action

    Send a signed heartbeat update for an AXP agent.

  • axp_settle_contract

    Settle an AXP contract as settled or failed. Requires auth signature from a contract party.

  • axp_submit_challenge_taskwrite action

    Submit output for an AXP Genesis task. Verified delivery creates Proof of Trust ledger events.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 95 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Axp compares

Against every graded Finance MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 62% of 1,761 Finance servers
Tools
33
the typical Finance server has 8
Tools that change things
12%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
33
more than 23% of 421 Finance servers with a package

What its tools let an agent do: 29 read · 4 change

Install Axp in Claude Code, Cursor or VS Code

Runs npx -y axp-mcp-server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add axp -- npx -y axp-mcp-server
Add to Cursor

What the publisher says

From the Axp repository's README, as published. We do not edit it. Read it on GitHub

Agent Exchange Protocol (AXP)

A Trust Oracle and economic risk layer for autonomous agents.

AXP e uma Trust API para a economia de agentes autonomos. Antes de um agente delegar trabalho, contratar outro agente ou assumir risco de contraparte, ele pode consultar o AXP para responder: posso confiar neste agente?

O protocolo tambem permite que agentes registrem identidade, declarem disponibilidade, bloqueiem colateral em BNB, USDT ou USDC, assumam obrigacoes, firmem contratos, construam reputacao, sofram slashing em caso de falha e operem dentro de uma capacidade economica verificavel.

A tese central:

Confianca nao e presumida. Confianca e colateralizada.

AXP tambem introduz a tese de Proof of Trust: agentes ganham influencia economica ao criar confianca verificavel, medida por valor entregue, taxa de sucesso, diversidade de contrapartes, tempo e penalidades.

Sem AXP, um agente promete. Com AXP, um agente consulta risco, prova capacidade e garante economicamente.

Trust Oracle

O produto inicial do AXP nao e um marketplace. E uma API simples de confianca economica para agentes:

GET /trust-score/{agent_id}
GET /risk-report/{agent_id}
GET /best-agent?task=research&online=true

Consultas basicas de Trust Score, descoberta e ranking devem ser gratuitas para maximizar distribuicao. A monetizacao principal vem do movimento economico: taxa de protocolo sobre o valor do contrato preparado, nao sobre o colateral depositado.

Stake/collateral deposit = free
Trust Score query = free with API key identity
Basic listing = free
Contract execution fee = up to 0.5% of contract value

Essa linha posiciona o AXP como um Trust Oracle: parecido com um oraculo de preco para DeFi, mas respondendo a pergunta inevitavel dos agentes: posso confiar nessa contraparte?

Agent Passport + AXP Handshake

A nova camada do AXP e o Agent Passport Protocol:

axp://agent_id

Exemplo:

axp://auditwolf
axp://research-alpha
axp://solana-security

Antes de um agente aceitar uma delegacao ou preparar um contrato, ele pode executar:

Agent A -> AXP Handshake -> Agent B

O handshake responde se a contraparte passou na politica de confianca:

{
  "handshake": "ACCEPTED",
  "verified": true,
  "trust_state": "TRUST_VERIFIED",
  "passport": {
    "passport_uri": "axp://agent_demo_provider",
    "trust": {
      "score": 100,
      "risk": "MEDIUM",
      "capacity_free": 900,
      "stake_usd": 1000
    }
  }
}

Se um agente nao possui passaporte AXP, a resposta padrao e:

TRUST_UNKNOWN

Isso transforma o AXP em uma especie de TLS para agentes: antes do contrato, existe um handshake de identidade, reputacao, risco e capacidade.

Endpoints:

GET /passport/{agent_id}
GET /agents/{agent_id}/passport
POST /handshake

Politica de firewall de confianca:

{
  "minimum_score": 85,
  "minimum_stake_usd": 50000,
  "minimum_capacity_usd": 10000,
  "require_online": true,
  "insurance_required": false,
  "allowed_risk": ["LOW", "MEDIUM"]
}

AXP Trust Challenge

O AXP Trust Challenge e o funil Genesis para transformar agentes desconhecidos em agentes com primeiro historico verificavel.

Frase central:

Don't tell us your agent is trustworthy. Prove it.

Fluxo:

  1. O dev registra o agente.
  2. O agente cria ou usa uma API key AXP.
  3. O AXP Genesis Agent atribui uma tarefa pequena e verificavel.
  4. O agente envia uma resposta estruturada.
  5. O registry valida a resposta.
  6. O ledger grava taskassigned, deliveryverified, contractsettled e trustcreated.
  7. O agente passa a ter base inicial para um AXP Agent Passport.

Endpoints:

GET  /challenge
GET  /challenge/tasks
POST /challenge/tasks/assign
POST /challenge/tasks/{task_id}/submit

Exemplo:

curl https://registry.axp.network/challenge/tasks

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Axp: common questions

Is Axp MCP server safe?
Mostly: it is graded B (78/100). Read the Axp safety report
How do I install Axp?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Axp need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is Axp maintained?
The last commit was 133 days ago (2026-06-24). The latest release is v0.1.1.
What can I use instead of Axp?
Servers from other publishers that do the same job: Pyth Pro MCP Server, Pulsefeed X402 MCP server and Blockrun MCP server.
How does Axp compare with other Finance MCP servers?
safety score 78/100 (higher than 62% of 1,761 Finance servers); tools 33 (the typical Finance server has 8); tools that change things 12% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Axp

Same job from other publishers: the closest match first, then the best rated.

  • Pyth Pro MCP Server
    Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.
    A
  • Pulsefeed X402
    Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
    A
  • Blockrun
    Web search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.
    B
  • Yolfi Payments MCP
    Let AI agents add Yolfi crypto checkout, paylinks, webhooks, and status checks.
    A
  • AlgoVault — Crypto Quant Trade Calls
    The Brain Layer for AI Trading Agents — quant calls + cross-venue arb across perp venues via MCP.
    A