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.

JarvisClaw — AI Gateway & API Marketplace

REMOTE · API.JARVISCLAW.AI · 2 COMPONENTS · SCANNED SEP 20

320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key.

0 this week 76 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 Security57
Transport & Reachability100
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1280 tokens (~98/item across 13 items; 9 tools + 4 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 95% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "chat" implies "send" 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 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
  • Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the JarvisClaw — AI Gateway & API Marketplace MCP server?

JarvisClaw — AI Gateway & API Marketplace is a hosted endpoint at https://api.jarvisclaw.ai/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 · api.jarvisclaw.ai

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

  • 30 Aug 26 0
    • Tool “aip_execute_with_budget” rewrote its description, which is the text the model reads security
    • Tool “aip_resolve” rewrote its description, which is the text the model reads security
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: 0.97 → pass security
  • 24 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 6 Aug 26 0
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 9 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
    • Schema quality: unverified → fail functional
    • Tool coverage: unverified → 100 functional
    • Schema quality: fail → pass functional
    • Schema quality: fair → good functional
    • Stability: fail → 0.37 functional
    • New resource “AIP (Agent Intent Protocol)” functional
    • New resource “API Marketplace” functional
    • New resource “Available Models” functional
    • New resource “Pricing Info” functional
    • New tool “aip_execute_with_budget” functional
    • New tool “aip_list_intents” functional
    • New tool “aip_resolve” functional
    • New tool “chat” functional
    • New tool “discover_agents” functional
    • New tool “get_api_detail” functional
    • New tool “aip_estimate_cost” functional
    • New tool “search_apis” functional
    • New tool “list_models” functional
  • 5 Aug 26 0
    • Stability: 0.30 → fail security
    • A breaking change shipped without a version bump: still 1.0.0 security
    • Tool “aip_estimate_cost” was removed security
    • Tool “aip_execute_with_budget” was removed security
    • Tool “aip_list_intents” was removed security
    • Tool “aip_resolve” was removed security
    • Tool “chat” was removed security
    • Tool “discover_agents” was removed security
    • Tool “get_api_detail” was removed security
    • Tool “list_models” was removed security
    • Tool “search_apis” was removed 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
    • Schema quality: fail → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: pass → fail functional
    • Resource “AIP (Agent Intent Protocol)” was removed functional
    • Resource “API Marketplace” was removed functional
    • Resource “Available Models” was removed functional
    • Resource “Pricing Info” was removed functional
    • Schema quality: good → fair functional
  • 1 Aug 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “search_apis” rewrote its description, which is the text the model reads security
    • Tool “get_api_detail” rewrote its description, which is the text the model reads security
    • “search_apis” reworded the description of “query” cosmetic
    • “search_apis” reworded the description of “category” cosmetic
    • “get_api_detail” reworded the description of “slug” cosmetic
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://api.jarvisclaw.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=jarvisclaw.ai CN=YE1,O=Let's Encrypt,C=US 30 Jul 2026 28 Oct 2026 ECDSA 256 ECDSA-SHA384 6b9deebb1027b35bed047ae6b45415ba1b5
SANs: *.jarvisclaw.ai, jarvisclaw.ai
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.jarvisclaw.ai. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
jarvisclaw.ai. 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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.jarvisclaw.ai/mcp Verified 200
http (plaintext) http://api.jarvisclaw.ai/mcp HTTPS enforced 301 https://api.jarvisclaw.ai/mcp
MCP tools · 9 exposed · ~1,017 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
aip_estimate_cost ~63

Preview what a task will cost before committing — get an estimated price for an intent without running it or spending anything. Ideal for budget planning and comparing options up front. Free.

NameTypeReqDescription
intentstringyesThe intent type
optimize_forstring

No output schema declared.

No examples provided.

aip_execute_with_budget ~175

Run an AI task end-to-end with a hard spending cap you set. This is the primary AIP action: it resolves the best provider, runs a risk check, pre-deducts against your budget, executes the call, and settles on-chain via x402 — all in one step. You never overspend past max_total_usd, and settlement is automatic. Supports chat, image, video, speech, prompt optimization, web search, and knowledge search intents.

NameTypeReqDescription
intentstringyesThe intent type
max_total_usdnumberMaximum budget for this request in USD (hard cap)
payloadobjectyesThe actual request payload (e.g. {model, messages} for chat, {prompt, size} for images)
preferred_paymentstringPayment method preference

No output schema declared.

No examples provided.

aip_list_intents ~58

Browse every AI task type AIP can route — chat, image, video, speech, web search, knowledge search — with a short description of each. Call this first to see what's on the menu before you resolve or execute. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

aip_resolve ~193

Find the best AI provider for a task and get ranked, priced options before you commit a cent. Pass a known intent type (chat_completion, code_execution, code_generation, data_analysis, document_processing, image_generation, knowledge_search, prompt_optimization, text_to_speech, translation, utility, video_generation, web_search) for structured routing, or a plain-language query for semantic matching. Each match returns provider, model, live per-request price, and a ready-to-call endpoint. Free to call — no payment until you execute.

NameTypeReqDescription
featuresarrayRequired features (e.g. streaming, function_calling, vision)
intentstringyesThe intent type (e.g. chat_completion, image_generation)
max_price_usdnumberMaximum acceptable price per request in USD (optional filter)
optimize_forstringOptimization preference: cost, quality, or latency

No output schema declared.

No examples provided.

chat ~158

Send a chat completion to any model on JarvisClaw through one OpenAI-compatible endpoint — GPT, Claude, Gemini, DeepSeek, and more. Pass a specific model ID or use 'auto' for smart routing to the best fit. One tool, every frontier model, no per-provider setup.

NameTypeReqDescription
max_tokensintegerMaximum tokens to generate. Optional.
messagesarrayyesChat messages array.
modelstringyesModel ID (e.g. 'gpt-4o', 'claude-sonnet-4-6-20250514', 'gemini-2.0-flash'). Use 'auto' for smart routing.
temperaturenumberSampling temperature (0-2). Optional.

No output schema declared.

No examples provided.

discover_agents ~99

Find other AI agents registered on JarvisClaw and connect to them directly. Search by capability, category, or name to get each agent's MCP URL and API endpoints — so your agent can delegate, collaborate, or chain work with others in the network.

NameTypeReqDescription
categorystringFilter by category.
searchstringSearch query (matches agent name and description).
tagsstringComma-separated tags to filter by.

No output schema declared.

No examples provided.

get_api_detail ~91

Get the full spec for any API returned by search_apis — pricing, method, and the exact request to send. Works for both a user-published API slug and a catalogue handle like 'federation/40'. Use this before wiring a call in.

NameTypeReqDescription
slugstringyesA user-published API slug, or a catalogue handle ('federation/40' or just '40').

No output schema declared.

No examples provided.

list_models ~56

List every AI model available on JarvisClaw — GPT, Claude, Gemini, DeepSeek, and more — with the model IDs you plug straight into the chat tool. Free, and the fastest way to see what you can call.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

search_apis ~124

Search every API on JarvisClaw — thousands of callable endpoints across search, blockchain, image, data, document and more, plus APIs other developers have published. Returns the exact invocation path and per-call price for each result, so you can call one directly afterwards. Free to search; you only pay when you invoke.

NameTypeReqDescription
categorystringOptional category filter, e.g. 'search', 'blockchain', 'image', 'data', 'document', 'storage'.
querystringSearch query (matches name, description, tags and category).

No output schema declared.

No examples provided.

Common questions

What is the JarvisClaw — AI Gateway & API Marketplace MCP server?

JarvisClaw — AI Gateway & API Marketplace is an MCP server listed in the public MCP registry as io.github.api-jarvisclaw/jarvisclaw. 320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key. This page covers its hosted endpoint (https://api.jarvisclaw.ai/mcp).

Is the JarvisClaw — AI Gateway & API Marketplace MCP server safe to use?

JarvisClaw — AI Gateway & API Marketplace scores 76 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 JarvisClaw — AI Gateway & API Marketplace MCP server expose?

JarvisClaw — AI Gateway & API Marketplace exposes 9 tools: list_models, chat, search_apis, get_api_detail, discover_agents, and 4 more. Their descriptions and schemas cost roughly 1,017 tokens of context every time the server is loaded.

Does the JarvisClaw — AI Gateway & API Marketplace MCP server require authentication?

No. We connected to JarvisClaw — AI Gateway & API Marketplace without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the JarvisClaw — AI Gateway & API Marketplace MCP server still maintained?

JarvisClaw — AI Gateway & API Marketplace 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.