AINumbers Fintech Intelligence Suite

co.ainumbersv0.4.10Updated Sep 29, 2026

530 MCP tools across 561 fintech tools: ChainGraph AP2 decisions, execution_hash. Zero PII.

VerifiedStreamable HTTPWeb executableOther

Installation

In SourceWeft

  1. Open AINumbers Fintech Intelligence Suite in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "tools": {
      "type": "http",
      "url": "https://mcp.ainumbers.co/mcp"
    }
  }
}

README

AINumbers MCP Apps Server

[CI] [License: MIT]

An agent calling a fintech tool by name has no way to know if the tool actually ran the math it claims to have run. This server closes that gap for the AINumbers.co suite: every tool call is deterministic, zero PII, and served straight from the suite's own single-file HTML, not a paraphrase of it.

An MCP Apps (SEP-1865) server that exposes the AINumbers.co fintech tool suite to any MCP host, including Claude, ChatGPT, M365 Copilot, VS Code, and Cursor.

[baas_provider_comparator, one of the flagship widget tools, the same HTML MCP Apps hosts render inline in chat]

Quick start

bash
# Claude: Settings -> Connectors -> Add custom connectorhttps://mcp.ainumbers.co/mcp
# Inspectornpx @modelcontextprotocol/inspector   # then Streamable HTTP -> the URL above

No auth, no API key, no account. Production runs on Cloudflare Workers (/healthz reports runtime: cloudflare-workers), so there are no cold starts. Cursor and other Open Plugins directories pick this repo up automatically via the root .mcp.json, which declares the same endpoint.

Live endpoint: https://mcp.ainumbers.co/mcp (streamable HTTP) · Docs: ainumbers.co/mcp.html · Registry: co.ainumbers/tools on the Official MCP Registry

Run your own (org-hosted)

[Deploy to Cloudflare]

Fork this repo and deploy the button above to run the same server inside your own Cloudflare account: no auth to add, no build step at deploy time, the Worker boots straight from the data/ and kernels/ already committed here.

Two edits to wrangler.jsonc before that first deploy will succeed on a fresh account:

  • routes points at mcp.ainumbers.co, a zone this fork doesn't own. Rename name and either delete routes (ship on the free workers.dev subdomain) or point it at a zone in your own account.
  • queues / workflows feed an internal analytics loop and are guarded in code (if (env.EVENTS_QUEUE), if (env.RENEWAL_WATCH_WORKFLOW)) — the MCP handshake and every tool call work without them. Queues need a Workers Paid plan; drop both blocks to stay free-tier.

Everything else, including the ASSETS binding serving the committed tool data, works unmodified. Full write-up (WAF rate-limit recipe, re-vendor cadence, conformance-attestation offer): ainumbers.co/mcp.html#deploy-your-own.

Tools

Read-only MCP tools — count intentionally not hardcoded here (it drifted stale the last time it was). See data/counts.json for the live figure; never hand-type this number, scripts/surface-parity.mjs and the site repo's count-drift gate both check against it. The flagship widgets below render as interactive widgets, the rest are ChainGraph compute nodes plus a handful of catalog and discovery utility tools: list_ainumbers_tools, find_tool, find_chain, build_workflow_links, run_chain, verify_execution_hash, build_chaingraph, emit_chaingraph_artifact, build_session_receipt.

Every tool declares readOnlyHint: true. No account, no auth, zero PII, nothing mutates state.

The flagship widgets

Each renders as the actual single-file AINumbers tool, served as a text/html;profile=mcp-app resource and driven by the AIN Bridge (prefill, run, Policy Mandate export). This table IS the enumeration — its row count is the widget count, never a number typed elsewhere:

MCP toolAINumbers tool
baas_provider_comparatorT152 BaaS Provider Comparator
validate_ap2_mcp_policyT320 AP2 MCP Policy Validator & Bridge
build_google_ap2_mandateT285 Google AP2 Checkout/Payment Mandate Builder
score_mcp_readinessT288 MCP Developer Readiness Scorecard
agentic_mandate_sandboxRBE-06 Agentic Mandate Sandbox
customer_risk_ratingT110 Customer Risk Rating Engine
ap2_aml_mandate_builderT131 AP2 AML Mandate Builder
lint_mcp_tool_definitionT274 MCP Tool-Definition Linter
validate_mcp_server_jsonT275 MCP server.json Validator
compare_agentic_payment_protocolsT276 Agentic Payments Protocol Comparator
decode_x402_paymentT277 x402 Decoder & 402 Flow Simulator
audit_mcp_oauthT278 MCP OAuth 2.1 Authorization Auditor
scan_tool_poisoningT282 MCP Tool-Poisoning Scanner
validate_a2a_agent_cardT283 A2A Agent Card Validator
inspect_visa_tap_signatureT286 Visa TAP Signature Inspector
run_kernel_vmKernel VM Widget

list_ainumbers_tools and find_tool search the full catalog (see data/counts.json for the current tool count) and return deep-links. Prefill-enabled tools accept #in=<base64url(JSON of {element_id: value})>[&run=1] for one-click invocation. find_chain and build_workflow_links return ordered deep-links for a named multi-tool workflow. run_chain executes one server-side; each run returns an OpenTelemetry span document as a resource link (one execute_tool span per executed step under an invoke_agent parent). verify_execution_hash independently re-verifies a returned artifact's hash.

Architecture

../repo (site repo, PostOakLabs/ainumbers)   |  chaingraph.json, manifests/, pilot.mjs-referenced tool HTML   |   v  node generate.mjs (build-time only, cannot run in cloud CI, needs the sibling repo)data/       vendored: chaingraph.json, catalog.json, manifests, counts.jsonkernels/    vendored: server-side compute kernels   |   vworker.mjs  (Cloudflare Workers, this repo's live runtime)server.mjs  (Node/express variant, local dev only, not deployed)   |   vhttps://mcp.ainumbers.co/mcp   (the one live endpoint: the Worker, not the express variant)

data/ and kernels/ are generated, committed artifacts. The Worker boots from what's committed, not from a live read of ../repo. Any change to chaingraph.json, a manifest, pilot.mjs, or a kernel in the site repo requires re-running generate.mjs here and committing data/ and kernels/ in the same push, or the worker deploys stale.

Deploy flow (CI-owned)

Branch, then PR. CI runs the validate job: tool-name collisions, surface-parity, kernel coverage, chain validation, vendor-freshness, and a wrangler deploy --dry-run. Merging to master runs the deploy job, which runs wrangler deploy against Cloudflare Workers, then a post-deploy /mcp smoke test (a real initialize call against the live endpoint). No manual wrangler deploy, ever: Cloudflare Workers Builds stays disconnected on purpose, since running both is a double-deployer and has caused outages before. A green CI bundle does not by itself prove the live handshake works; only the smoke step does.

Dependabot auto-merges every dependency update (patch, minor, and major, all CI-gated), so run git pull --rebase before pushing any local branch since master moves on its own.

Independent monitoring

[MCP Queen grade]

MCP Queen is a third-party operational probe: it continuously re-checks the live /mcp endpoint's protocol handshake and tool-schema responses and grades what it observes. This is not a security or compliance attestation, ours or theirs — it describes observable server behavior only.

Develop

bash
npm installnode generate.mjs   # re-vendor tool HTML + manifests + catalog + kernels from ../repo into data/ + kernels/npm start           # http://localhost:3300/mcp (+ /healthz), Node/express variant (server.mjs), local dev onlynode scripts/check-tool-names.mjs   # verify no mcp_name collision before pushingnode scripts/surface-parity.mjs     # verify counts.json matches the registered surface

pilot.mjs is the single source of truth for the widget tool set. After changing any pilot tool in the site repo, run node generate.mjs, commit data/ and kernels/, and push. CI validates and deploys.

All tool content is client-side, deterministic, and zero PII. Code is MIT licensed (see LICENSE); content is CC BY 4.0, Post Oak Labs. See README-SPEC.md for architecture and history.

Transport conformance (MCP-STREAMABLE-HTTP-CONFORMANCE-1). The /mcp door is a full Streamable HTTP endpoint per the MCP spec (2025-03-26 / 2025-06-18): initialize issues an Mcp-Session-Id (echoed thereafter, never required — the server is stateless behind the scenes), GET /mcp with Accept: text/event-stream and that session id opens a server-to-client SSE stream with a 25 s keepalive that closes on disconnect (a session-less GET keeps the spec-clean 405 + Allow it always gave), DELETE /mcp with the session id ends the session with 204 (a bare DELETE stays 405), an unknown MCP-Protocol-Version is a JSON-RPC 400 (never a 500), and tools/list honours params.cursor/returns nextCursor (page size TOOLS_LIST_PAGE_SIZE in worker.mjs is deliberately ≥ the whole surface for one release). Verify any door — local (node server.mjs) or production — with the zero-dependency six-check script: bash scripts/transport-conformance.sh [BASE_URL].

Idempotency & retry (RUN-1-1). Every tool call is deterministic: a safe retry is a re-run that returns a byte-identical artifact (generated_at/opened_at differ; hashes do not), and run_chain echoes a stable dedupe: { input_hash, composite_execution_hash } for client-side dedupe. Dedupe is a cache concern, not a correctness concern. The not-stateless carve-outs (RenewalWatchWorkflow, scheduled(), queue(), MRTR_STATE_KEY requestState, the input_required flow, shared-cache hints, the null-strip live-vs-golden drift class) are documented in docs/IDEMPOTENCY.md; the KV/Cache receipt cache (D2) stays deferred.

Source: README.md at commit c0c3f87

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.4.10LatestSep 16, 2026