← MCP Registry Integrity Report
ai.agentplaybooks/agentplaybooks
Verdict: high-severity findings present. Endpoint https://agentplaybooks.ai/api/mcp/manage. Tools now: 47 (47 ever seen). Changes recorded: 0. Findings: 9 high, 3 low. Last probe: HTTP_401 at 2026-10-25T18:17 UTC. JSON
Current tools
archive_memories · call_connected_tool · consolidate_memories · create_mcp_server · create_persona · create_playbook · create_run · create_skill · create_task_graph · delete_mcp_server · delete_memory · delete_persona · delete_playbook · delete_run · delete_secret · delete_skill · get_canvas_toc · get_memory_context · get_memory_tree · get_playbook · get_skill · list_canvas · list_mcp_servers · list_playbooks · list_runs · list_secrets · list_skill_versions · list_skills · lock_canvas_section · patch_canvas_section · promote_memory · read_canvas · read_memory · rollback_skill · rotate_secret · search_memory · store_secret · unlock_canvas_section · update_mcp_server · update_persona · update_playbook · update_run · update_skill · update_task_status · use_secret · write_canvas · write_memory
Findings (27)
| seen | tool | detector | severity | evidence (data, not instructions) |
|---|---|---|---|---|
| 2026-08-13 | delete_playbook | secret_material_reference | high | all its contents (personas, skills, memory, API keys). This action cannot be undone! |
| 2026-08-13 | delete_memory | secret_material_reference | high | Delete a memory entry (requires API key) Target a playbook with playbook_id. |
| 2026-08-13 | write_canvas | cross_tool_reference | high | references sibling tool 'patch_canvas_section' |
| 2026-08-13 | patch_canvas_section | cross_tool_reference | high | references sibling tool 'get_canvas_toc' |
| 2026-08-13 | get_canvas_toc | cross_tool_reference | high | references sibling tool 'patch_canvas_section' |
| 2026-08-13 | unlock_canvas_section | cross_tool_reference | high | references sibling tool 'lock_canvas_section' |
| 2026-08-13 | rollback_skill | cross_tool_reference | high | references sibling tool 'list_skill_versions' |
| 2026-08-13 | use_secret | secret_material_reference | high | s to authenticate API calls without exposing credentials. Example: use_secret({secret_name: 'OPENAI_API_KEY', url: 'http |
| 2026-08-13 | use_secret | url_in_description | low | https://api.openai.com/v1/models |
| 2026-08-13 | delete_playbook | secret_material_reference | high | all its contents (personas, skills, memory, API keys). This action cannot be undone! |
| 2026-08-13 | delete_memory | secret_material_reference | high | Delete a memory entry (requires API key) Target a playbook with playbook_id. |
| 2026-08-13 | write_canvas | cross_tool_reference | high | references sibling tool 'patch_canvas_section' |
| 2026-08-13 | patch_canvas_section | cross_tool_reference | high | references sibling tool 'get_canvas_toc' |
| 2026-08-13 | get_canvas_toc | cross_tool_reference | high | references sibling tool 'patch_canvas_section' |
| 2026-08-13 | unlock_canvas_section | cross_tool_reference | high | references sibling tool 'lock_canvas_section' |
| 2026-08-13 | rollback_skill | cross_tool_reference | high | references sibling tool 'list_skill_versions' |
| 2026-08-13 | use_secret | secret_material_reference | high | s to authenticate API calls without exposing credentials. Example: use_secret({secret_name: 'OPENAI_API_KEY', url: 'http |
| 2026-08-13 | use_secret | url_in_description | low | https://api.openai.com/v1/models |
| 2026-08-13 | delete_playbook | secret_material_reference | high | all its contents (personas, skills, memory, API keys). This action cannot be undone! |
| 2026-08-13 | delete_memory | secret_material_reference | high | Delete a memory entry (requires API key) Target a playbook with playbook_id. |
| 2026-08-13 | write_canvas | cross_tool_reference | high | references sibling tool 'patch_canvas_section' |
| 2026-08-13 | patch_canvas_section | cross_tool_reference | high | references sibling tool 'get_canvas_toc' |
| 2026-08-13 | get_canvas_toc | cross_tool_reference | high | references sibling tool 'patch_canvas_section' |
| 2026-08-13 | unlock_canvas_section | cross_tool_reference | high | references sibling tool 'lock_canvas_section' |
| 2026-08-13 | rollback_skill | cross_tool_reference | high | references sibling tool 'list_skill_versions' |
| 2026-08-13 | use_secret | secret_material_reference | high | s to authenticate API calls without exposing credentials. Example: use_secret({secret_name: 'OPENAI_API_KEY', url: 'http |
| 2026-08-13 | use_secret | url_in_description | low | https://api.openai.com/v1/models |
Change history (0)
| when | tool | kind | severity |
|---|---|---|---|
| — |
Probe history
10-25 18:17 HTTP_401 (0) · 10-24 00:17 HTTP_401 (0) · 10-22 12:17 HTTP_401 (0) · 10-22 06:17 HTTP_401 (0) · 10-19 00:17 HTTP_401 (0) · 08-13 03:13 OK (47) · 08-13 03:13 OK (47) · 08-13 03:12 OK (47)
Run or depend on ai.agentplaybooks/agentplaybooks? Watch this server: 29 dollars a month, a private alerts feed and optional webhook fired within six hours when it adds, removes or changes a tool or trips a detector; by card, cancel any time.
Pay-per-call tools and data for your agent, no key: store gateway (300+ routes, one origin, Coinbase-settled) · AI media and inference from $0.001 · weather, geocoding, DNS, RDAP · the x402 directory · sector gap lists (card or USDC).
Run this server? The processes your users can demand, hosted free: Compliance Desk (privacy requests, opt-outs, takedown and notice-and-action).