# AIBITIOUS 404 LAB - 32 Free Agent Experiments (remote · aibitious.com)

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

- Trust score: 65/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `aibitious.com`: 65/100 (this document), [markdown](https://verifymcp.io/servers/aibitious-agent404/404-mcp.md), [page](https://verifymcp.io/servers/aibitious-agent404/404-mcp)

## Channel facts

- Endpoint: `https://aibitious.com/404/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1733 tokens (~52/item across 33 items; 33 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 33 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 33 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server?

AIBITIOUS 404 LAB - 32 Free Agent Experiments is a hosted endpoint at https://aibitious.com/404/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http aibitious-agent404 'https://aibitious.com/404/mcp/'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.aibitious-agent404]
url = "https://aibitious.com/404/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "aibitious-agent404": {
      "type": "remote",
      "url": "https://aibitious.com/404/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add aibitious-agent404 --url 'https://aibitious.com/404/mcp/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  aibitious-agent404:
    url: "https://aibitious.com/404/mcp/"
```

### Netclaw

```json
{
  "McpServers": {
    "aibitious-agent404": {
      "Transport": "http",
      "Url": "https://aibitious.com/404/mcp/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add aibitious-agent404 -t streamable-http -u 'https://aibitious.com/404/mcp/'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 61, +1)

- [security] The server changed its declared name: AIBITIOUS 404 LAB - Ten Agent Experiments → AIBITIOUS 404 LAB - 32 Agent Experiments
- [functional regression] Schema quality: 42 → 52
- [functional] New tool “approval_packet”
- [functional] New tool “boundary_cases”
- [functional] New tool “budget_envelope”
- [functional] New tool “check_claim_provenance”
- [functional] New tool “citation_matrix”
- [functional] New tool “context_budget”
- [functional] New tool “duplicate_actions”
- [functional] New tool “evidence_expiry”
- [functional] New tool “manifest_drift”
- [functional] New tool “minimize_agent_data”
- [functional] New tool “permission_paths”
- [functional] New tool “plan_workflow_recovery”
- [functional] New tool “prerequisite_gate”
- [functional] New tool “queue_forecast”
- [functional] New tool “receipt_chain”
- [functional] New tool “release_gate”
- [functional] New tool “retry_schedule”
- [functional] New tool “schema_impact”
- [functional] New tool “scope_delta”
- [functional] New tool “simulate_agent_action_policy”
- [functional] New tool “slo_burn”
- [functional] New tool “triage_webhook_deliveries”

### 2026-11-11 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 59, −1)

- [security] The server changed its declared name: AIBITIOUS 404 - Official CVE Evidence → AIBITIOUS 404 LAB - Ten Agent Experiments
- [functional improvement] Schema quality: 50 → 42
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “csv_data_doctor”
- [functional] New tool “http_headers_audit”
- [functional] New tool “invoice_math_audit”
- [functional] New tool “json_schema_guard”
- [functional] New tool “json_shape_diff”
- [functional] New tool “mcp_registry_preflight”
- [functional] New tool “openapi_contract_preflight”
- [functional] New tool “robots_policy_check”
- [functional] New tool “secret_pattern_shield”

### 2026-11-09 (score 60)

First indexed and scored.

## MCP tools (33)

### `resolve_public_fact` (~58 tokens)

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.

Input parameters:

- `identifier` (string, required)

### `report_missing_information` (~43 tokens)

Opt-in report of a PUBLIC missing-data topic, never include private data or secrets.

Input parameters:

- `consent_to_aggregate` (boolean)
- `topic` (string, required)

### `json_schema_guard` (~41 tokens)

Validate one JSON object against a SAFE subset of JSON Schema. No remote refs. Offline.

Input parameters:

- `document` (object, required)
- `schema` (object, required)

### `csv_data_doctor` (~50 tokens)

Find missing fields, ragged CSV rows and duplicate key values; no raw rows are stored.

Input parameters:

- `csv_text` (string, required)
- `delimiter` (string)
- `key_columns`

### `invoice_math_audit` (~60 tokens)

Independently recalculate invoice arithmetic, NOT legal/tax compliance. Synthetic data only.

Input parameters:

- `currency` (string)
- `declared_gross`
- `declared_net`
- `declared_tax`
- `lines` (array, required)

### `secret_pattern_shield` (~33 tokens)

Detect probable token patterns without returning or storing secret values. Never send real secrets.

Input parameters:

- `text` (string, required)

### `openapi_contract_preflight` (~37 tokens)

Static OpenAPI 3.x lint: missing operation IDs, responses and malformed operations. Offline.

Input parameters:

- `spec` (object, required)

### `mcp_registry_preflight` (~33 tokens)

Check a candidate MCP server.json metadata structure; this is NOT official validation.

Input parameters:

- `server` (object, required)

### `http_headers_audit` (~31 tokens)

Assess supplied HTTP security response headers. No network or live website probe.

Input parameters:

- `headers` (object, required)

### `robots_policy_check` (~46 tokens)

Evaluate supplied robots.txt for one agent/path. Not a legal scraping permission.

Input parameters:

- `agent` (string)
- `path` (string)
- `robots_txt` (string, required)

### `json_shape_diff` (~38 tokens)

Compare JSON object shapes for added, deleted or changed field types. Offline.

Input parameters:

- `after` (object, required)
- `before` (object, required)

### `simulate_agent_action_policy` (~42 tokens)

Dry-run one proposed tool action against explicit allow/deny/approval rules; no enforcement.

Input parameters:

- `action` (object, required)
- `rules` (array, required)

### `plan_workflow_recovery` (~33 tokens)

Plan reverse-order compensations for a supplied workflow DAG; never execute actions.

Input parameters:

- `steps` (array, required)

### `triage_webhook_deliveries` (~35 tokens)

Find duplicate, failed and rate-limited deliveries from supplied HTTP status metadata.

Input parameters:

- `attempts` (array, required)

### `check_claim_provenance` (~41 tokens)

Check whether supplied claim references reach at least one declared source; not fact checking.

Input parameters:

- `claims` (array, required)
- `sources` (array, required)

### `minimize_agent_data` (~48 tokens)

Check declared fields, retention and model transfer against a supplied local policy.

Input parameters:

- `allowed_fields` (array, required)
- `fields` (array, required)
- `max_retention_days` (integer, required)

### `scope_delta` (~52 tokens)

Permission 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.

Input parameters:

- `payload` (object, required)

### `approval_packet` (~74 tokens)

Approval Packet Check

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.

Input parameters:

- `payload` (object, required)

### `budget_envelope` (~67 tokens)

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.

Input parameters:

- `payload` (object, required)

### `retry_schedule` (~56 tokens)

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.

Input parameters:

- `payload` (object, required)

### `duplicate_actions` (~69 tokens)

Idempotency Audit

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.

Input parameters:

- `payload` (object, required)

### `prerequisite_gate` (~57 tokens)

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.

Input parameters:

- `payload` (object, required)

### `evidence_expiry` (~61 tokens)

Evidence Freshness

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.

Input parameters:

- `payload` (object, required)

### `citation_matrix` (~58 tokens)

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.

Input parameters:

- `payload` (object, required)

### `schema_impact` (~60 tokens)

Consumer 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.

Input parameters:

- `payload` (object, required)

### `boundary_cases` (~55 tokens)

Boundary Case Builder

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.

Input parameters:

- `payload` (object, required)

### `slo_burn` (~57 tokens)

SLO Burn Check

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.

Input parameters:

- `payload` (object, required)

### `queue_forecast` (~59 tokens)

Queue Capacity 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.

Input parameters:

- `payload` (object, required)

### `permission_paths` (~58 tokens)

Permission Path Explorer

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.

Input parameters:

- `payload` (object, required)

### `context_budget` (~57 tokens)

Context Budget Packer

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.

Input parameters:

- `payload` (object, required)

### `release_gate` (~54 tokens)

Release Gate Check

Require named checks to be green before a release. Offline check. Supply payload like {"required":["test"],"checks":[{"id":"test","status":"success"}]}. Advisory result only.

Input parameters:

- `payload` (object, required)

### `manifest_drift` (~49 tokens)

Manifest Drift

Compare expected and observed resource manifests. Offline check. Supply payload like {"expected":{"version":"1"},"observed":{"version":"2"}}. Advisory result only.

Input parameters:

- `payload` (object, required)

### `receipt_chain` (~121 tokens)

Receipt Chain Check

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.

Input parameters:

- `payload` (object, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/aibitious-agent404/404-mcp#diagnostics

## Score history

- 2026-11-21: 65
- 2026-11-20: 65
- 2026-11-19: 64
- 2026-11-18: 64
- 2026-11-17: 64
- 2026-11-16: 63
- 2026-11-15: 63
- 2026-11-14: 62
- 2026-11-13: 62
- 2026-11-12: 61
- 2026-11-11: 60
- 2026-11-10: 59
- 2026-11-09: 60

## Common questions

### What is the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server?

AIBITIOUS 404 LAB - 32 Free Agent Experiments is an MCP server listed in the public MCP registry as io.github.aibitious/agent404. 32 free tools: CVE/data checks and offline agent decisions on permissions, budgets and recovery. This page covers its hosted endpoint (https://aibitious.com/404/mcp/).

### Is the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server safe to use?

AIBITIOUS 404 LAB - 32 Free Agent Experiments scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server expose?

AIBITIOUS 404 LAB - 32 Free Agent Experiments exposes 33 tools: resolve_public_fact, report_missing_information, json_schema_guard, csv_data_doctor, invoice_math_audit, and 28 more. Their descriptions and schemas cost roughly 1,733 tokens of context every time the server is loaded.

### Does the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server require authentication?

No. We connected to AIBITIOUS 404 LAB - 32 Free Agent Experiments without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server still maintained?

AIBITIOUS 404 LAB - 32 Free Agent Experiments is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server?

VerifyMCP ran 12 checks on AIBITIOUS 404 LAB - 32 Free Agent Experiments, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about AIBITIOUS 404 LAB - 32 Free Agent Experiments: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://aibitious.com/404/mcp/
- Repository: https://github.com/aibitious/ai-micropayment-network
- Changelog RSS feed: https://verifymcp.io/servers/aibitious-agent404/404-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/aibitious-agent404/404-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/aibitious-agent404/404-mcp.json
- HTML version of this page: https://verifymcp.io/servers/aibitious-agent404/404-mcp
