Skip to content

AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server

io.github.aibitious/agent404aibitiousstreamable-httpv0.3.0Scanned

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

33 tools: 22 change things and 11 only read.

Tools: 0 delete, 0 irreversible, 22 write, 11 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 3 findings

Tools listed without sign-in. Remote posture

With Anlyon

22 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server can do

The AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server is published by the GitHub account aibitious. It has 33 tools. It can create or change data (22 tools: report_missing_information, invoice_math_audit, secret_pattern_shield, openapi_contract_preflight and 18 more), but cannot delete data. 11 tools only read.

1 tool brings in text other people can write (triage_webhook_deliveries).

The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 12, 2026, version 0.3.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

33 tools

Changes things 22Claude Code: ask
  • boundary_casesGenerate bounded edge cases from simple field constraints.1 finding

    Why it is in this group

    • The description's first verb is "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "boundary_cases" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • budget_envelopeCheck worst-case proposed cost against a local hard budget.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • check_claim_provenanceCheck whether supplied claim references reach at least one declared source; not fact checking.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check whether supplied claim references reach at least one declared source; not fact checking.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • context_budgetSelect prioritized context chunks inside a token limit.1 finding

    Why it is in this group

    • The description's first verb is "select": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "context_budget" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "select": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • evidence_expiryFlag stale observations before an agent acts.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • http_headers_auditAssess supplied HTTP security response headers.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Assess supplied HTTP security response headers. No network or live website probe.
  • invoice_math_auditIndependently recalculate invoice arithmetic, NOT legal/tax compliance.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Independently recalculate invoice arithmetic, NOT legal/tax compliance. Synthetic data only.
  • mcp_registry_preflightCheck a candidate MCP server.json metadata structure; this is NOT official validation.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check a candidate MCP server.json metadata structure; this is NOT official validation.
  • minimize_agent_dataCheck declared fields, retention and model transfer against a supplied local policy.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check declared fields, retention and model transfer against a supplied local policy.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • openapi_contract_preflightStatic OpenAPI 3.x lint: missing operation IDs, responses and malformed operations.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Static OpenAPI 3.x lint: missing operation IDs, responses and malformed operations. Offline.
  • plan_workflow_recoveryPlan reverse-order compensations for a supplied workflow DAG; never execute actions.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Plan reverse-order compensations for a supplied workflow DAG; never execute actions.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • prerequisite_gateCheck whether all declared evidence prerequisites are present.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • queue_forecastProject backlog and drain time from supplied rates.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • receipt_chainCheck links in a supplied digest receipt chain.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • release_gateRequire named checks to be green before a release.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Require named checks to be green before a release. Offline check. Supply payload like {"required":["test"],"checks":[{"id":"test","status":"success"}]}. Advisory result only.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • report_missing_informationOpt-in report of a PUBLIC missing-data topic, never include private data or secrets.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Opt-in report of a PUBLIC missing-data topic, never include private data or secrets.
  • retry_schedulePreview capped exponential retries against a deadline.1 finding

    Why it is in this group

    • The name "retry_schedule" says "schedule": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "retry_schedule" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "retry_schedule" says "schedule": a word for a change.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • robots_policy_checkEvaluate supplied robots.txt for one agent/path.No findings

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    Description, as the server wrote it
    Evaluate supplied robots.txt for one agent/path. Not a legal scraping permission.
  • schema_impactIdentify downstream consumers broken by changed fields.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • secret_pattern_shieldDetect probable token patterns without returning or storing secret values.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Detect probable token patterns without returning or storing secret values. Never send real secrets.
  • simulate_agent_action_policyDry-run one proposed tool action against explicit allow/deny/approval rules; no enforcement.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Dry-run one proposed tool action against explicit allow/deny/approval rules; no enforcement.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • slo_burnMeasure error-budget burn against a supplied target.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
Only reads 11Show 11 read-only tools
  • approval_packetFind missing or expired fields before seeking human approval.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • citation_matrixFind claims with missing or unknown citation identifiers.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find claims with missing or unknown citation identifiers. Offline check. Supply payload like {"claims":[{"id":"claim1","citation_refs":["src1"]}],"citations":["src1"]}. Advisory result only.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • csv_data_doctorFind missing fields, ragged CSV rows and duplicate key values; no raw rows are stored.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find missing fields, ragged CSV rows and duplicate key values; no raw rows are stored.
  • duplicate_actionsFind duplicate attempts and conflicting key reuse.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • json_schema_guardValidate one JSON object against a SAFE subset of JSON Schema.No findings

    Why it is in this group

    • The description's first verb is "validate": a word for reading.
    Description, as the server wrote it
    Validate one JSON object against a SAFE subset of JSON Schema. No remote refs. Offline.
  • json_shape_diffCompare JSON object shapes for added, deleted or changed field types.No findings

    Why it is in this group

    • The name "json_shape_diff" says "diff": a word for reading.
    Description, as the server wrote it
    Compare JSON object shapes for added, deleted or changed field types. Offline.
  • manifest_driftCompare expected and observed resource manifests.No findings

    Why it is in this group

    • The description's first verb is "compare": a word for reading.
    Description, as the server wrote it
    Compare expected and observed resource manifests. Offline check. Supply payload like {"expected":{"version":"1"},"observed":{"version":"2"}}. Advisory result only.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • permission_pathsFind sensitive targets reachable through declared capability edges.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • resolve_public_factResolve one CVE identifier (e.g.No findings

    Why it is in this group

    • The name "resolve_public_fact" says "resolve": a word for reading.
    Description, as the server wrote it
    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.
  • scope_deltaFind newly granted permissions outside an approved set.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find newly granted permissions outside an approved set. Offline check. Supply payload like {"before":["read"],"after":["read","send"],"approved_additions":[]}. Advisory result only.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true
  • triage_webhook_deliveriesFind duplicate, failed and rate-limited deliveries from supplied HTTP status metadata.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "find" and "http": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Find duplicate, failed and rate-limited deliveries from supplied HTTP status metadata.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 17, 2026, 15:21 UTC, unchanged since Nov 17, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
22
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 22 tools that change things (22 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://aibitious.com/404/mcp/: tools/list returned 33 tools to an anonymous client, including report_missing_information (write), invoice_math_audit (write), secret_pattern_shield (write), openapi_contract_preflight (write), mcp_registry_preflight (write) and 17 more

    What this check looks for

Posture changes

  1. Nov 17, 2026
    • Tools that change things, listed without credentials: 7 to 22

Findings

Matches of fixed checks, with the text they matched.

3 warn
  • The server marks "retry_schedule" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "retry_schedule" says "schedule": a word for a change.

    What this check looks for
  • The server marks "boundary_cases" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "generate": a word for a change.

    What this check looks for
  • The server marks "context_budget" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "select": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 7 -> 22.View diff
    • Tools that change things, listed without credentials: 7 to 22
  2. Tools22 added.+22 addedView diff
  3. Tools9 added.+9 addedView diff

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent404__resolve_public_fact",
      "mcp__agent404__json_schema_guard",
      "mcp__agent404__csv_data_doctor",
      "mcp__agent404__json_shape_diff",
      "mcp__agent404__triage_webhook_deliveries",
      "mcp__agent404__scope_delta",
      "mcp__agent404__approval_packet",
      "mcp__agent404__duplicate_actions",
      "mcp__agent404__citation_matrix",
      "mcp__agent404__permission_paths",
      "mcp__agent404__manifest_drift"
    ],
    "ask": [
      "mcp__agent404__report_missing_information",
      "mcp__agent404__invoice_math_audit",
      "mcp__agent404__secret_pattern_shield",
      "mcp__agent404__openapi_contract_preflight",
      "mcp__agent404__mcp_registry_preflight",
      "mcp__agent404__http_headers_audit",
      "mcp__agent404__robots_policy_check",
      "mcp__agent404__simulate_agent_action_policy",
      "mcp__agent404__plan_workflow_recovery",
      "mcp__agent404__check_claim_provenance",
      "mcp__agent404__minimize_agent_data",
      "mcp__agent404__budget_envelope",
      "mcp__agent404__retry_schedule",
      "mcp__agent404__prerequisite_gate",
      "mcp__agent404__evidence_expiry",
      "mcp__agent404__schema_impact",
      "mcp__agent404__boundary_cases",
      "mcp__agent404__slo_burn",
      "mcp__agent404__queue_forecast",
      "mcp__agent404__context_budget",
      "mcp__agent404__release_gate",
      "mcp__agent404__receipt_chain"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent404. Review it before you use it.

Capability tags behind 1 rule
  • mcp__agent404__triage_webhook_deliveries untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.aibitious/agent404/verify?hash=87eb15c297166601bd112aee3f363cfcb17e2c1a077cbc2e023b62870af647c9" | jq -e '.changed == false'

Pinned hash 87eb15c29716, from Nov 12, 2026, 11:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.aibitious/agent404/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.aibitious/agent404
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.aibitious/agent404.svg)](https://radar.anlyon.com/servers/io.github.aibitious/agent404)

Source: MCP Registry · repository. Synced Nov 12, 2026, 11:17 UTC.

AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

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

No scan can promise that. What its definitions show: 33 tools, 22 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

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

33 tools: 22 write, 11 read. report_missing_information, invoice_math_audit, secret_pattern_shield, openapi_contract_preflight, mcp_registry_preflight, http_headers_audit, robots_policy_check, simulate_agent_action_policy and 25 more.

Does the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the AIBITIOUS 404 LAB - 32 Free Agent Experiments MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.