# AIBITIOUS 404 LAB - 32 Free Agent Experiments

> 32 free tools: CVE/data checks and offline agent decisions on permissions, budgets and recovery.

- name: io.github.aibitious/agent404
- version: 0.3.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 88/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.aibitious%2Fagent404
- tools: https://api.protogrid.dev/v1/servers/io.github.aibitious%2Fagent404/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agent404": {
      "type": "http",
      "url": "https://aibitious.com/404/mcp/"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% +updated-2d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (new)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 88 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- warn `tools.annotations`: only 22 of 33 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 22 of 33 tools declare all four hints; missing: json_schema_guard (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); invoice_math_audit (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); robots_policy_check (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 3,581 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`, `stability.new_links`: tool history recorded for 4 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 33, about 3,581 tokens to load them all
- tool set hash: 282181b68309364e6ce7ba768d964038
- tools last changed: 2026-11-12T14:57:38.565Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.aibitious/agent404.svg)](https://protogrid.dev/servers/io.github.aibitious/agent404)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-12 `receipt_chain` added
  - Check links in a supplied digest receipt chain. Offline check. Supply payload like {"root_sha256":"0000000000000000000000000000000000000000000000000000000000000000","receipts":[{"previous_sha256":"0000000000000000000000000000000000000000000000000000000000000000","sha256":"1111111111111111111111111111111111111111111111111111111111111111"}]}. Advisory result only.
- 2026-11-12 `manifest_drift` added
  - Compare expected and observed resource manifests. Offline check. Supply payload like {"expected":{"version":"1"},"observed":{"version":"2"}}. Advisory result only.
- 2026-11-12 `release_gate` added
  - Require named checks to be green before a release. Offline check. Supply payload like {"required":["test"],"checks":[{"id":"test","status":"success"}]}. Advisory result only.
- 2026-11-12 `context_budget` added
  - Select prioritized context chunks inside a token limit. Offline check. Supply payload like {"max_tokens":100,"chunks":[{"id":"source1","tokens":40,"priority":10}]}. Advisory result only.
- 2026-11-12 `permission_paths` added
  - Find sensitive targets reachable through declared capability edges. Offline check. Supply payload like {"start":"agent","edges":[{"from":"agent","to":"secret"}],"sensitive_targets":["secret"]}. Advisory result only.
- 2026-11-12 `queue_forecast` added
  - Project backlog and drain time from supplied rates. Offline check. Supply payload like {"backlog":100,"incoming_per_hour":10,"capacity_per_hour":20,"horizon_hours":4}. Advisory result only.
- 2026-11-12 `slo_burn` added
  - Measure error-budget burn against a supplied target. Offline check. Supply payload like {"target_percent":"99","total":1000,"bad":20,"alert_burn_rate":2}. Advisory result only.
- 2026-11-12 `boundary_cases` added
  - Generate bounded edge cases from simple field constraints. Offline check. Supply payload like {"fields":[{"name":"count","type":"integer","minimum":0,"maximum":10}]}. Advisory result only.
- 2026-11-12 `schema_impact` added
  - Identify downstream consumers broken by changed fields. Offline check. Supply payload like {"before":{"id":1},"after":{},"consumers":[{"id":"client","required_fields":["id"]}]}. Advisory result only.
- 2026-11-12 `citation_matrix` added
  - Find claims with missing or unknown citation identifiers. Offline check. Supply payload like {"claims":[{"id":"claim1","citation_refs":["src1"]}],"citations":["src1"]}. Advisory result only.

Full history: https://api.protogrid.dev/v1/servers/io.github.aibitious%2Fagent404/changes

## Remotes

- https://aibitious.com/404/mcp/ (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (33)

- `approval_packet`: Find missing or expired fields before seeking human approval. Offline check. Supply payload like {"now_unix":100,"action":{"actor":"agent","tool":"mail.send","target":"draft1","effect":"send","reason":"owner_request","expiry_unix":200}}. Advisory result only.
- `boundary_cases`: Generate bounded edge cases from simple field constraints. Offline check. Supply payload like {"fields":[{"name":"count","type":"integer","minimum":0,"maximum":10}]}. Advisory result only.
- `budget_envelope`: Check worst-case proposed cost against a local hard budget. Offline check. Supply payload like {"limit_usd":"0","spent_usd":"0","reserved_usd":"0","proposed_worst_case_usd":"0"}. Advisory result only.
- `check_claim_provenance`: Check whether supplied claim references reach at least one declared source; not fact checking.
- `citation_matrix`: Find claims with missing or unknown citation identifiers. Offline check. Supply payload like {"claims":[{"id":"claim1","citation_refs":["src1"]}],"citations":["src1"]}. Advisory result only.
- `context_budget`: Select prioritized context chunks inside a token limit. Offline check. Supply payload like {"max_tokens":100,"chunks":[{"id":"source1","tokens":40,"priority":10}]}. Advisory result only.
- `csv_data_doctor`: Find missing fields, ragged CSV rows and duplicate key values; no raw rows are stored.
- `duplicate_actions`: Find duplicate attempts and conflicting key reuse. Offline check. Supply payload like {"calls":[{"idempotency_key":"k1","payload_fingerprint":"hash1"},{"idempotency_key":"k1","payload_fingerprint":"hash1"}]}. Advisory result only.
- `evidence_expiry`: Flag stale observations before an agent acts. Offline check. Supply payload like {"now_unix":200,"records":[{"id":"health","observed_unix":100,"ttl_seconds":120}]}. Advisory result only.
- `http_headers_audit`: Assess supplied HTTP security response headers. No network or live website probe.
- `invoice_math_audit`: Independently recalculate invoice arithmetic, NOT legal/tax compliance. Synthetic data only.
- `json_schema_guard`: Validate one JSON object against a SAFE subset of JSON Schema. No remote refs. Offline.
- `json_shape_diff`: Compare JSON object shapes for added, deleted or changed field types. Offline.
- `manifest_drift`: Compare expected and observed resource manifests. Offline check. Supply payload like {"expected":{"version":"1"},"observed":{"version":"2"}}. Advisory result only.
- `mcp_registry_preflight`: Check a candidate MCP server.json metadata structure; this is NOT official validation.
- `minimize_agent_data`: Check declared fields, retention and model transfer against a supplied local policy.
- `openapi_contract_preflight`: Static OpenAPI 3.x lint: missing operation IDs, responses and malformed operations. Offline.
- `permission_paths`: Find sensitive targets reachable through declared capability edges. Offline check. Supply payload like {"start":"agent","edges":[{"from":"agent","to":"secret"}],"sensitive_targets":["secret"]}. Advisory result only.
- `plan_workflow_recovery`: Plan reverse-order compensations for a supplied workflow DAG; never execute actions.
- `prerequisite_gate`: Check whether all declared evidence prerequisites are present. Offline check. Supply payload like {"requirements":[{"id":"deploy","evidence_refs":["ci"]}],"available_evidence":["ci"]}. Advisory result only.
- `queue_forecast`: Project backlog and drain time from supplied rates. Offline check. Supply payload like {"backlog":100,"incoming_per_hour":10,"capacity_per_hour":20,"horizon_hours":4}. Advisory result only.
- `receipt_chain`: Check links in a supplied digest receipt chain. Offline check. Supply payload like {"root_sha256":"0000000000000000000000000000000000000000000000000000000000000000","receipts":[{"previous_sha256":"0000000000000000000000000000000000000000000000000000000000000000","sha256":"1111111111111111111111111111111111111111111111111111111111111111"}]}. Advisory result only.
- `release_gate`: Require named checks to be green before a release. Offline check. Supply payload like {"required":["test"],"checks":[{"id":"test","status":"success"}]}. Advisory result only.
- `report_missing_information`: Opt-in report of a PUBLIC missing-data topic, never include private data or secrets.
- `resolve_public_fact`: Resolve one CVE identifier (e.g. CVE-2024-3094) using NIST NVD records.
    This tool does not execute code, scan targets, or accept arbitrary URLs.
    
- `retry_schedule`: Preview capped exponential retries against a deadline. Offline check. Supply payload like {"attempts":3,"first_delay_seconds":2,"max_delay_seconds":10,"deadline_seconds":30}. Advisory result only.
- `robots_policy_check`: Evaluate supplied robots.txt for one agent/path. Not a legal scraping permission.
- `schema_impact`: Identify downstream consumers broken by changed fields. Offline check. Supply payload like {"before":{"id":1},"after":{},"consumers":[{"id":"client","required_fields":["id"]}]}. Advisory result only.
- `scope_delta`: Find newly granted permissions outside an approved set. Offline check. Supply payload like {"before":["read"],"after":["read","send"],"approved_additions":[]}. Advisory result only.
- `secret_pattern_shield`: Detect probable token patterns without returning or storing secret values. Never send real secrets.
- `simulate_agent_action_policy`: Dry-run one proposed tool action against explicit allow/deny/approval rules; no enforcement.
- `slo_burn`: Measure error-budget burn against a supplied target. Offline check. Supply payload like {"target_percent":"99","total":1000,"bad":20,"alert_burn_rate":2}. Advisory result only.
- `triage_webhook_deliveries`: Find duplicate, failed and rate-limited deliveries from supplied HTTP status metadata.