# A2A Agent Card Monitor – Skills & Contract Changes

Monitor public A2A Agent Cards for skill, interface, version and advertised authentication changes. Export source-linked contract snapshots without invoking agents or accessing protected cards.

Canonical product page: https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/

## Example input

```json
{
  "cardUrls": [
    "https://preflight.abacore.net/.well-known/agent-card.json",
    "https://www.agentcard.net/.well-known/agent-card.json"
  ],
  "maxResults": 2
}
```

## Ready-to-use input recipes

These are downloadable JSON configurations. They do not start runs or represent public Apify saved tasks. Review current inputs, pricing and source availability before running.

[Default input](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/input.json) · [Input schema](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/input-schema.json) · [Saved output capture](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/evidence.json)

### Compare two public Agent Card contracts

Read ACN Preflight and AgentCard.net Toolkit public metadata. This does not call any advertised skill.

```json
{
  "cardUrls": [
    "https://preflight.abacore.net/.well-known/agent-card.json",
    "https://www.agentcard.net/.well-known/agent-card.json"
  ],
  "maxResults": 2
}
```

[Download JSON](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/examples/recipe-1.json) · [Example evidence](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/examples/recipe-1.evidence.json)

Historical successful run recorded 2026-11-21 UTC, with 2 saved rows. This does not establish current availability.

### Inspect a domain’s public discovery card

Resolve AgentCard.net to its standard well-known card and export its declared skills and interfaces.

```json
{
  "cardUrls": [
    "https://www.agentcard.net"
  ],
  "maxResults": 1
}
```

[Download JSON](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/examples/recipe-2.json) · [Example evidence](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/examples/recipe-2.evidence.json)

Historical successful run recorded 2026-11-21 UTC, with 1 saved rows. This does not establish current availability.

### Start a public agent contract change watch

Establish a private baseline for the two public example cards; later complete runs identify skill and contract changes.

```json
{
  "cardUrls": [
    "https://preflight.abacore.net/.well-known/agent-card.json",
    "https://www.agentcard.net/.well-known/agent-card.json"
  ],
  "maxResults": 2,
  "comparePrevious": true,
  "snapshotName": "agent-contract-watch"
}
```

[Download JSON](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/examples/recipe-3.json) · [Example evidence](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/examples/recipe-3.evidence.json)

Historical successful run recorded 2026-11-21 UTC, with 2 saved rows. This does not establish current availability.

[All example inputs](https://mayd-it.com/data-tools/actors/a2a-agent-card-change-monitor/examples/index.json)
## Choose this tool

For AI integration agencies, agent directory operators and developers maintaining a shortlist of public A2A services.

Useful output columns: `title`, `agentVersion`, `protocolFamily`, `skillCount`, `skills`, `interfaces`, `securitySchemes`, `addedSkills`, `removedSkills`.

## Practical workflow

Read only public well-known Agent Cards, normalize their declared capabilities and compare complete observations before reviewing an integration change.

## Check the fit

Reads public metadata only; it never invokes a skill, performs a payment, or requests a protected extended card. Advertised capabilities and signatures are not executed or cryptographically verified. Only standard and legacy well-known paths, no query strings, redirects, credentials or private-network targets.

## Real output sample

One selected row from a 2026-11-21 run. Selected original scalar fields from one actual saved observation; nested data and private artifact links omitted.

Run: xmYqtAtOUGgOHnLg8. Summary status: ok. Incomplete: false.

Dated bounded private release evidence for this exact input/build. This does not establish current values, whole-source coverage or fleet health.

```json
{
  "recordId": "a2a-card:d38c0fb53fd987ffc9d1755bca5e2bfb9d4e022e614a268d425e75fefe3104d9",
  "title": "ACN Preflight",
  "agentVersion": "1.1.0",
  "protocolFamily": "1.x",
  "skillCount": 3,
  "interfacesChanged": null,
  "authChanged": null,
  "comparisonStatus": "not_requested",
  "sourceUrl": "https://preflight.abacore.net/.well-known/agent-card.json",
  "url": "https://preflight.abacore.net/.well-known/agent-card.json",
  "observedAt": "2026-11-21T20:18:42.244Z"
}
```




## Full guide

![A2A Agent Card Monitor — illustrative workflow](https://mayd-it.com/assets/actor-banners/a2a-agent-card-change-monitor-fbc693b1cee9.png)

# A2A Agent Card Monitor – Skills & Contract Changes

Did a remote AI agent change its public skills, interfaces or authentication contract?

Spot public AI agent contract changes before you update your integration. Keep skill additions, removed skills, interface changes and advertised authentication changes in source-linked JSON or CSV.

## Start with a small useful result

For AI integration agencies, agent directory operators and developers maintaining a shortlist of public A2A services. No API key, account login or proxy is required. Press **Start** to collect at most two real public observations. Leave comparison off for the first exploration. Every row includes a stable `recordId`, `title`, `url`, `sourceUrl` and `observedAt`.

## What you can do with the results

Each row represents one validated public card and includes `skills`, `interfaces`, `capabilities`, input/output modes, provider metadata and selected security scheme declarations, including API key location, advertised OAuth scopes, flow endpoint URLs and PKCE flags. `skillCount` counts advertised skills, not successful calls. Modern `supportedInterfaces` and legacy `url`/`preferredTransport` fields are normalized, while `cardLayout` keeps their origin visible and `protocolFamily` derives from the declared versions. Interface preference order and tenant routing values are preserved. Extra custom fields, call examples, signatures and secret-like scheme values are not copied.

## Three practical input recipes

### Compare two public Agent Card contracts

Read ACN Preflight and AgentCard.net Toolkit public metadata. This does not call any advertised skill.

```json
{
  "cardUrls": [
    "https://preflight.abacore.net/.well-known/agent-card.json",
    "https://www.agentcard.net/.well-known/agent-card.json"
  ],
  "maxResults": 2
}
```

### Inspect a domain’s public discovery card

Resolve AgentCard.net to its standard well-known card and export its declared skills and interfaces.

```json
{
  "cardUrls": [
    "https://www.agentcard.net"
  ],
  "maxResults": 1
}
```

### Start a public agent contract change watch

Establish a private baseline for the two public example cards; later complete runs identify skill and contract changes.

```json
{
  "cardUrls": [
    "https://preflight.abacore.net/.well-known/agent-card.json",
    "https://www.agentcard.net/.well-known/agent-card.json"
  ],
  "maxResults": 2,
  "comparePrevious": true,
  "snapshotName": "agent-contract-watch"
}
```

## Changes you can verify

On complete subsequent observations, `addedSkills`, `removedSkills` and `changedSkills` describe card-level changes. `interfacesChanged`, `authChanged` and `capabilitiesChanged` identify contract differences. Removed skills mean removed from the newly retrieved complete card; an unavailable card never establishes that an agent or skill was removed. Authentication requirements absent from a card remain null; an explicit empty list remains distinct.

Set `comparePrevious: true` and a stable `snapshotName` to retain a private baseline for the selected scope. The first complete run marks observations `new`; later runs mark them `changed` or `unchanged` with `changedFields` and the previous normalized observation. The baseline belongs to the account running the Actor. A different source list or comparison scope creates separate history.

`onlyChanges: true` enables comparison and suppresses unchanged rows; a successful repeat can legitimately save zero rows. Source failures, truncated output, a deadline or a spending limit preserve the prior baseline. A concurrent-history change detected before commit is reported rather than overwritten; avoid overlapping runs for the same watchlist because the storage service does not provide an atomic compare-and-swap transaction.

## Coverage and limits

- The default reads ACN Preflight and AgentCard.net Toolkit, two independent public examples. They are third-party services, not Mayd It services. Their metadata can change.
- Supply public domains or the exact `/.well-known/agent-card.json` path. Legacy `/.well-known/agent.json` is supported only when explicitly selected; no hidden fallback requests.
- Each source uses a read-only GET. Standard HTTP(S) ports only; URL credentials and query strings are refused. All resolved IP addresses must be public, and validated addresses are pinned for the connection to prevent DNS rebinding.
- Response bodies are limited to 512 KiB before and after decompression. Redirects are not followed; correct the public source URL when a card moves.
- A declared private interface is recorded with a warning and never contacted. A signature count is presence metadata only: `signatureVerification` is always `not_performed`.
- This is a bounded contract monitor, not a complete A2A conformance validator, agent marketplace, trust score, security audit, or uptime guarantee.
- At most 20 targets and 20 saved observations per run. Requests use a 120-second maximum run budget and the platform’s earlier deadline.
- All-source failure fails honestly. Source errors and access problems are written to `SUMMARY`, never fabricated as paid dataset rows. A partial run retains useful rows and clearly reports incomplete coverage.

## Output, pricing and scheduling

Export the dataset as JSON, CSV or Excel. Read `SUMMARY` for source coverage, limits and history status; open `RUN_REPORT` for a readable overview. For nested checks or skills, JSON preserves the full structure.

Base pricing is **$0.002 per confirmed saved observation**, plus **$0.00005 per Actor start** at the default 256 MB. Standard plan-tier discounts may apply to results. A row containing several checks or skills is still one observation. Failed sources and unchanged results suppressed by `onlyChanges` do not incur a result charge. Apify platform usage may also apply under your plan. The Actor checks remaining result allowance before saving, and the last accepted row at the limit is counted correctly.

For recurring checks, save a task with your watchlist and use Apify Schedules at a cadence appropriate to the upstream source. Configure integrations yourself if you need to deliver results elsewhere; this Actor sends no messages and creates no schedules.

## Source and interpretation

The [A2A specification](https://a2a-protocol.org/v1.0.1/specification/) defines public Agent Card discovery and metadata. [ACN Preflight card](https://preflight.abacore.net/.well-known/agent-card.json) and [AgentCard.net card](https://www.agentcard.net/.well-known/agent-card.json) are the documented examples. This is an independent tool, not an official A2A product.

Use the Actor’s Issues tab to report source changes or request a supported input example.

## Companion workflows

Each Actor runs separately with its own inputs, authorization and pricing. These instructions do not configure automatic execution.

### [MCP Registry Monitor - AI Integrations & Version Changes](https://apify.com/maydit/mcp-registry-change-monitor)

Maintain separate evidence for A2A agent contracts and MCP server registrations.

1. Review changed skills, versions and interface declarations in the public Agent Card.
2. Run the MCP registry monitor for separately selected relevant MCP servers.
3. Use both exports to maintain an integration inventory with source and observation timestamps.

A2A and MCP are different protocols. A declared capability or registry entry is not proof that execution works; no agent invocation is performed.

### [OpenAPI Contract Monitor - Operation & Schema Changes](https://apify.com/maydit/openapi-operation-change-monitor)

Review API contract changes for services that also expose public OpenAPI descriptions.

1. Identify a changed agent's public service interface from your own integration documentation.
2. Provide a verified public OpenAPI document URL to the OpenAPI monitor.
3. Compare the two contract-change reports before testing your integration.

An Agent Card URL is not an OpenAPI document. Do not automatically follow untrusted card links or transmit credentials.
