Skip to main content
Glama

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

# Claude: Settings -> Connectors -> Add custom connector
https://mcp.ainumbers.co/mcp

# Inspector
npx @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

Related MCP server: Xero MCP Server

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 tool

AINumbers tool

baas_provider_comparator

T152 BaaS Provider Comparator

validate_ap2_mcp_policy

T320 AP2 MCP Policy Validator & Bridge

build_google_ap2_mandate

T285 Google AP2 Checkout/Payment Mandate Builder

score_mcp_readiness

T288 MCP Developer Readiness Scorecard

agentic_mandate_sandbox

RBE-06 Agentic Mandate Sandbox

customer_risk_rating

T110 Customer Risk Rating Engine

ap2_aml_mandate_builder

T131 AP2 AML Mandate Builder

lint_mcp_tool_definition

T274 MCP Tool-Definition Linter

validate_mcp_server_json

T275 MCP server.json Validator

compare_agentic_payment_protocols

T276 Agentic Payments Protocol Comparator

decode_x402_payment

T277 x402 Decoder & 402 Flow Simulator

audit_mcp_oauth

T278 MCP OAuth 2.1 Authorization Auditor

scan_tool_poisoning

T282 MCP Tool-Poisoning Scanner

validate_a2a_agent_card

T283 A2A Agent Card Validator

inspect_visa_tap_signature

T286 Visa TAP Signature Inspector

run_kernel_vm

Kernel 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.json
kernels/    vendored: server-side compute kernels
   |
   v
worker.mjs  (Cloudflare Workers, this repo's live runtime)
server.mjs  (Node/express variant, local dev only, not deployed)
   |
   v
https://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

npm install
node 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 only
node scripts/check-tool-names.mjs   # verify no mcp_name collision before pushing
node 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.

Available Tools

16 tools
agentic_mandate_sandboxAgentic Mandate SandboxA
Read-onlyIdempotent
Inspect

Simulate agent payment policies for tokenized A2A corridors: set spend caps, MCC allowlists, velocity throttles, and approval thresholds; run synthetic transactions against the policy and export the result as a Policy Mandate. Browser-based, client-side only, zero PII. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

ap2_aml_mandate_builderAP2 AML Mandate BuilderB
Read-onlyIdempotent
Inspect

Anchor agentic tool for Cat-12. Translate AML/BSA program controls, TM rules, and customer risk policy into a structured Policy Mandate JSON for agentic payment sy Browser-based, client-side only. Zero PII. Link users to https://ainumbers.co/tools/131-ap2-aml-mandate-builder.html for interactive use. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

audit_mcp_oauthMCP OAuth 2.1 Authorization AuditorA
Read-onlyIdempotent
Inspect

Audit MCP OAuth 2.1 authorization: validate RFC 9728 protected-resource-metadata, check RFC 8707 audience binding, and assess token-passthrough / confused-deputy risk. Use when a developer is securing an MCP server's authorization. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

baas_provider_comparatorBaaS Provider ComparatorA
Read-onlyIdempotent
Inspect

Score and compare BaaS providers across 10 capability dimensions (regulatory standing, programme management, card issuance, rails, KYC/KYB, disputes, developer experience, pricing, FDIC pass-through, compliance tooling) with a user-adjustable 1-5 weighting matrix. Outputs a weighted comparison matrix and Markdown evaluation memo. Browser-based, client-side only, zero PII. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

build_google_ap2_mandateGoogle AP2 Checkout/Payment Mandate (VDC) Builder & ValidatorA
Read-onlyIdempotent
Inspect

Build or validate a Google AP2 Checkout/Payment Mandate VDC (Open/Closed). Targets the external AP2 spec, not the AINumbers Policy Mandate. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

compare_agentic_payment_protocolsAgentic Payments Protocol Comparator & Field CrosswalkA
Read-onlyIdempotent
Inspect

Compare agentic payment protocols (AP2, ACP/Shared Payment Token, x402, Visa TAP, Mastercard Agent Pay) across credential, signing, scope, rail, identity, and audit dimensions; optionally recommend a fit for a scenario. Use when a developer or strategist needs to orient across the fragmenting agentic-payments standards. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

customer_risk_ratingCustomer Risk Rating EngineA
Read-onlyIdempotent
Inspect

Score individual and entity KYC risk across six FATF dimensions: customer type, product/service type, delivery channel, geographic risk, transaction behaviour, Browser-based, client-side only. Zero PII. Link users to https://ainumbers.co/tools/110-customer-risk-rating.html for interactive use. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

decode_x402_paymentx402 Header Decoder, Payload Linter & 402 Flow SimulatorA
Read-onlyIdempotent
Inspect

Decode an x402 payment header or lint an exact-scheme PaymentPayload, and describe the HTTP-402 verify/settle flow. Use when a developer is integrating x402 and needs to inspect a header, check a payload shape, or understand the flow. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

inspect_visa_tap_signatureVisa Trusted Agent Protocol Signature Inspector & ReadinessA
Read-onlyIdempotent
Inspect

Inspect a Visa Trusted Agent Protocol HTTP Message Signature and score TAP readiness. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

lint_mcp_tool_definitionMCP Tool-Definition Linter & Annotation DesignerA
Read-onlyIdempotent
Inspect

Validate an MCP tool definition against JSON Schema 2020-12 and current naming, output-schema, and annotation rules; returns findings, a conformance score, and a recommended annotation set. Use when a developer wants to check an MCP tool definition before publishing. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

list_ainumbers_toolsList AINumbers toolsB
Read-onlyIdempotent
Inspect

Search the AINumbers catalog (420 client-side fintech tools). Returns deep-links; prefill-enabled tools accept #in=<base64url(JSON of {element_id: value})>[&run=1] for one-click invocation.

Inputs: query, category, limit.

scan_tool_poisoningMCP Tool-Poisoning & Prompt-Injection Manifest ScannerA
Read-onlyIdempotent
Inspect

Scan an MCP tool description/manifest for tool-poisoning and prompt-injection smells; returns a risk score and flagged patterns. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

score_mcp_readinessMCP Developer Readiness ScorecardA
Read-onlyIdempotent
Inspect

Compute a composite MCP server ship-readiness score across tool definitions, server.json, OAuth, transport, tool poisoning, and spec compliance. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

validate_a2a_agent_cardA2A Agent Card Validator & Extension CheckerA
Read-onlyIdempotent
Inspect

Validate an A2A agent-card.json against the v1.0 shape, check signatures, and confirm extension declarations. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

validate_ap2_mcp_policyAP2 MCP Policy Validator & BridgeA
Read-onlyIdempotent
Inspect

Validate AP2 Policy Mandate JSON payloads against the Unified Build Contract v1.0 schema. Auto-generates MCP tool definitions from the mandate and simulates agent ingestion of agent_instructions. Use when authoring or testing AP2 agentic payment policies. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

validate_mcp_server_jsonMCP server.json Validator & Registry-Ready Skeleton GeneratorA
Read-onlyIdempotent
Inspect

Validate an MCP server.json against the 2025-12-11 schema and the official registry publishing rules; returns findings, a registry-readiness score, and an optional compliant skeleton. Use when a developer wants to check a server.json before publishing to the MCP Registry. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Inputs: inputs.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 16 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes, such as MCP validation vs. payment protocol analysis. However, there is slight overlap among AP2-related tools (ap2_aml_mandate_builder, build_google_ap2_mandate, validate_ap2_mcp_policy) and MCP validation tools (lint_mcp_tool_definition, validate_mcp_server_json, score_mcp_readiness, audit_mcp_oauth) that could cause confusion if descriptions are not carefully read.

    Naming Consistency3/5

    The naming convention is mixed: some tools start with a verb (e.g., 'validate_mcp_server_json', 'scan_tool_poisoning') while others start with a noun (e.g., 'agentic_mandate_sandbox', 'customer_risk_rating'). All use snake_case, which is readable, but the lack of a consistent verb_noun pattern reduces clarity.

    Tool Count4/5

    With 16 tools, the server covers a broad range of fintech and MCP utilities without being excessive. The count is slightly high for a single domain, but each tool serves a specific purpose and the variety is justified by the toolkit nature of the server.

    Completeness3/5

    The tool set covers key areas like agentic payments, AML/KYC, MCP validation, and BaaS comparison. However, there are notable gaps: for MCP, only validation tools exist without creation/management tools; for payments, comparison and decoding are present but no payment creation tools. The surface is partially complete for a general fintech toolkit.

    Maintenance

    ActivityActive
    ResponsivenessUsually handled

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      F
      maintenance
      A server that enables interaction with Square's API via Goose, supporting queries for locations, customers, and more with context preservation and MCP-compliant responses.
      12
      4
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      A Model Context Protocol server implementation providing standardized access to Xero's accounting and business features, enabling operations like contact management, invoice creation, and chart of accounts management through MCP.
      51
      21,642 npm
      394
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      The Dodo Payments MCP Server integrates with agentic frameworks to provide a lightweight, serverless-compatible interface for AI-driven payment operations like billing, subscriptions, and customer management. It enables autonomous agents to securely act on behalf of users using the Dodo Payments
      909 npm
      54
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      53 regulatory compliance evidence tools across 3 MCP servers for AI agents. MiCA authorization status, DORA evidence packs, stablecoin risk scoring (105+ tokens), macro intelligence (86 FRED series). Every response ECDSA-signed (ES256K), blockchain-anchored, audit-ready. Free tier, OAuth 2.0.
      MIT