Low Risk

wayback_lookup

Retrieve Wayback Machine snapshots for a domain: first capture, latest, total count, snapshot list. Use to investigate domain history and age; for full audit use domain_report. Free: 30/hr, Pro: 500/hr. status='ok' means the count is authoritative (even when 0 → confirmed no archives). status='un...

Part of the ContrastAPI MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call wayback_lookup to retrieve information from ContrastAPI without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though wayback_lookup only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

contrastcyber-contrastapi.yaml
tools:
  wayback_lookup:
    rules:
      - action: allow

See the full ContrastAPI policy for all 53 tools.

Tool Name wayback_lookup
Category Read
Risk Level Low

View all 53 tools →

Agents calling read-class tools like wayback_lookup have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the wayback_lookup tool do? +

Retrieve Wayback Machine snapshots for a domain: first capture, latest, total count, snapshot list. Use to investigate domain history and age; for full audit use domain_report. Free: 30/hr, Pro: 500/hr. status='ok' means the count is authoritative (even when 0 → confirmed no archives). status='unavailable' means CDX timed out/rate-limited/5xx — total_snapshots is OMITTED (unknown, NOT zero) and the agent should NOT report "no snapshots"; the warnings[] array carries the cdx_* error code (cdx_timeout/cdx_rate_limited/cdx_unavailable/cdx_error/cdx_parse_error/cdx_body_too_large). Heavy domains (kernel.org, microsoft.com, archive.org itself) frequently time out the CDX endpoint despite having millions of snapshots — fall back to archive_url for manual inspection. Returns {domain, status, total_snapshots, first_seen, last_seen, years_online, snapshots, archive_url, summary, warnings}.. It is categorised as a Read tool in the ContrastAPI MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on wayback_lookup? +

Add a rule in your Intercept YAML policy under the tools section for wayback_lookup. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the ContrastAPI MCP server.

What risk level is wayback_lookup? +

wayback_lookup is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit wayback_lookup? +

Yes. Add a rate_limit block to the wayback_lookup rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block wayback_lookup completely? +

Set action: deny in the Intercept policy for wayback_lookup. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides wayback_lookup? +

wayback_lookup is provided by the ContrastAPI MCP server (contrastcyber/contrastapi). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.