// SCAN REPORT

Metis Public Health

277 tools. 121 can modify or destroy data without limits.

9 destructive tools with no built-in limits. Policy required.

Last updated: 5 Sept 2026

121 can modify or destroy data

156 read-only

277 tools total

Community server · catalogue entry checked 05/09/2026

How to control Metis Public Health ↓

TOOL MAP

What Metis Public Health exposes to your agents

Read (156) Write / Execute (109) Destructive / Financial (9)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Metis Public Health tools

Destructive · High reset_thinking_profile This tool permanently deletes all thinking_profile_events and overwrites the thinking-profile.yaml configuration file. Destructive · High delete_data_trigger This tool irreversibly removes data triggers from the system without recourse for recovery. Destructive · High delete_knowledge_database Irreversibly deletes user's indexed PDF library and knowledge data; no undo possible. Destructive · High delete_task The tool name 'delete_task' clearly indicates deletion of task data, which is destructive and cannot be undone.

121 of Metis Public Health's 277 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Metis Public Health

PolicyLayer is an MCP gateway — it sits between your AI agents and Metis Public Health, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "archive_library_item": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_glossary_term": {
    "limits": [
      {
        "counter": "add_glossary_term_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "aggregate_reflexions": {
    "limits": [
      {
        "counter": "aggregate_reflexions_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Metis Public Health — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON METIS PUBLIC HEALTH →

Instant setup, no code required.

FULL CATALOGUE

All 277 Metis Public Health tools

DESTRUCTIVE 9 tools

Destructive archive_library_item archive_library_item Destructive delete_data_trigger Delete a data trigger permanently. Destructive delete_knowledge_database delete_knowledge_database Destructive delete_task delete_task Destructive remove_first_run_marker Delete the .first-run marker file to signal that the config wizard is complete. Destructive remove_library_item remove_library_item Destructive remove_project remove_project Destructive remove_tracked_file remove_tracked_file Destructive reset_thinking_profile Clear all thinking_profile_events and reset thinking-profile.yaml to defaults.

EXECUTE 11 tools

Execute analyze_script analyze_script Execute dhis2_query dhis2_query Execute generate_profiling_script generate_profiling_script Execute install_background_pack install_background_pack Execute run_maintenance run_maintenance Execute run_metis run_metis Execute run_trigger_now Manually execute a data trigger right now. Execute scaffold_script scaffold_script Execute scan_project_scripts scan_project_scripts Execute start_course_build start_course_build Execute start_interest_interview start_interest_interview

WRITE 98 tools

Write add_glossary_term add_glossary_term Write add_journal_entry Store a journal entry with auto-extracted mood and energy. Write add_memory_entry add_memory_entry Write add_reminder add_reminder Write add_specialist_context add_specialist_context Write add_tracked_file add_tracked_file Write add_user_topic Add a topic to track for new publications. Write apply_proposal apply_proposal Write approve_proposal Approve a pending skill improvement proposal and apply it. Write archive_project Archive a project — marks it inactive but keeps all data. Write build_pdf_knowledge_db build_pdf_knowledge_db Write capture_idea capture_idea Write capture_observation capture_observation Write commit_session_decisions commit_session_decisions Write configure_library_provider configure_library_provider Write connect_project_folder connect_project_folder Write consolidate_session_memory consolidate_session_memory Write create_document create_document Write create_focus_area create_focus_area Write create_knowledge_database create_knowledge_database Write create_presentation create_presentation Write create_project create_project Write create_project_full create_project_full Write create_task create_task Write draft_self_improvement_proposal draft_self_improvement_proposal Write export_background_pack export_background_pack Write focus_keep Save an item to a focus area's safe, for further reflection. Write generate_daily_insight generate_daily_insight Write generate_handoff_brief generate_handoff_brief Write generate_image generate_image Write import_bibtex_library Import papers from a BibTeX file into literature_metadata. Write import_zotero_pdfs import_zotero_pdfs Write index_library_pdfs index_library_pdfs Write index_pdf_library index_pdf_library Write ingest_ideas_document ingest_ideas_document Write kg_index_memory kg_index_memory Write link_claude_desktop Register a Metis project in Claude Desktop's project list. Write link_memories link_memories Write log_agent_run log_agent_run Write log_consent_event log_consent_event Write mark_brief_read mark_brief_read Write mark_publications_read mark_publications_read Write promote_basket_item Move a basket item to a stable project folder (promote from basket to active storage). Write promote_session_decisions promote_session_decisions Write propose_library_organization propose_library_organization Write publish_course publish_course Write push_to_zotero push_to_zotero Write reading_stack_add Put something in the reading stack, or change what state it is in. Write record_dataset_treatment record_dataset_treatment Write record_decision record_decision Write record_research_finding record_research_finding Write record_routing_preference record_routing_preference Write register_code_artifact register_code_artifact Write register_data_dictionary register_data_dictionary Write register_data_trigger register_data_trigger Write reject_proposal reject_proposal Write resolve_decision resolve_decision Write restore_db restore_db Write review_open_decisions Walk the decisions waiting on you, most-repeated first. Write save_brainstorm_output save_brainstorm_output Write save_course_curriculum save_course_curriculum Write save_course_outline save_course_outline Write save_course_sources save_course_sources Write save_daily_brief save_daily_brief Write save_lesson_draft save_lesson_draft Write save_review save_review Write save_session_event save_session_event Write save_session_summary save_session_summary Write save_viz_exemplar save_viz_exemplar Write save_viz_recipe save_viz_recipe Write save_viz_style save_viz_style Write scan_literature Scan inputs/literature/ for new PDFs and register them in literature_metadata. Write set_backup_schedule set_backup_schedule Write set_discovery_tips Adjust the feature-tips preference (the user's control). Write set_focus_state set_focus_state Write set_knowledge_layer_enabled set_knowledge_layer_enabled Write set_network_policy set_network_policy Write set_project_category set_project_category Write set_research_interests set_research_interests Write set_working_memory set_working_memory Write store_episodic_memory store_episodic_memory Write store_procedural_memory store_procedural_memory Write store_semantic_memory store_semantic_memory Write sync_zotero_library sync_zotero_library Write sync_zotero_local sync_zotero_local Write toggle_context Activate or deactivate a specialist context. Write unarchive_project Restore an archived project to active status. Write update_all_projects Scan all registered project folders for activity. Refreshes CLAUDE.md for each. Write update_contact Add or update a contact record. Write update_data_trigger update_data_trigger Write update_focus_overview update_focus_overview Write update_project_memory update_project_memory Write update_task update_task Write update_thinking_profile update_thinking_profile Write update_today_board update_today_board Write write_reflexion write_reflexion Write write_user_config write_user_config Write write_user_preferences write_user_preferences

READ 156 tools

Read aggregate_reflexions aggregate_reflexions Read anonymize_text anonymize_text Read ask_library ask_library Read assemble_brainstorm_context assemble_brainstorm_context Read audit_background_provenance audit_background_provenance Read backup_db backup_db Read check_data_safety Scan content for PII patterns and classify sensitivity level. Read check_for_newer_evidence check_for_newer_evidence Read check_news_feeds check_news_feeds Read check_viz_fit check_viz_fit Read citation_debt citation_debt Read clean_dataset clean_dataset Read compare_profiles compare_profiles Read consolidate_old_memories consolidate_old_memories Read consolidate_reflexions consolidate_reflexions Read cross_pollinate Find cross-domain connections for given text. Read daily_note daily_note Read decrypt_backup decrypt_backup Read detect_projects detect_projects Read dhis2_metadata dhis2_metadata Read diff_anonymization Return a unified diff comparing original and anonymized text. Read discovery_intro Return the tiny first-run orientation — the 3-5 highest-value capabilities. Read discovery_status discovery_status Read encrypt_backup encrypt_backup Read enrich_meeting_with_crossrefs enrich_meeting_with_crossrefs Read evaluate_against_layers evaluate_against_layers Read export_citations export_citations Read export_knowledge_markdown export_knowledge_markdown Read extract_structured extract_structured Read find_connections find_connections Read find_tools find_tools Read find_viz find_viz Read focus_brief Everything on one focus area: what is saved, what is new, what is open. Read focus_decline Say an item does not interest you, so similar ones rank lower in future. Read focus_explore Answer a question against a focus area's own corpus, notes and ideas. Read focus_safe What is in a focus area's safe, and what it has learned to cool on. Read full_scan full_scan Read get_agent_context get_agent_context Read get_agent_runs get_agent_runs Read get_backup_schedule Return the current backup schedule configuration. Read get_brainstorm_session Retrieve all turns in a brainstorm session. Read get_briefing_coverage get_briefing_coverage Read get_consent_ledger get_consent_ledger Read get_constitution get_constitution Read get_contacts Retrieve all contacts from the contacts table. Read get_context get_context Read get_continuity_context get_continuity_context Read get_course_status Return the current status of a course build (or all active builds). Read get_daily_insight Retrieve a stored daily insight. Read get_glossary Retrieve all glossary terms. Read get_ideas get_ideas Read get_journal get_journal Read get_library_stats get_library_stats Read get_memory_health Generate a health report for the memory palace. Read get_missed_news get_missed_news Read get_network_policy Return the current network access policy. Read get_new_publications Retrieve new publications, optionally filtered by topic. Read get_news_briefs get_news_briefs Read get_pdf_index_stats get_pdf_index_stats Read get_pending_proposals List all skill improvement proposals awaiting review. Read get_persona_learnings get_persona_learnings Read get_project_categories get_project_categories Read get_project_status get_project_status Read get_related_memories get_related_memories Read get_research_context get_research_context Read get_spans Fetch recent agent spans, optionally filtered by session or run. Read get_tasks get_tasks Read get_thinking_profile Read and return the current thinking profile from system/thinking-profile.yaml. Read get_topic_memory Return all memory entries tagged with a specific topic, newest first. Read get_user_config get_user_config Read get_user_profile get_user_profile Read get_user_topics Return all active topics from user_topics. Read get_working_memory Retrieve working memory for a session, or the most recent entries if no session given. Read index_pending_layers index_pending_layers Read ingest_office_document ingest_office_document Read ingest_profiling_output ingest_profiling_output Read kg_community kg_community Read kg_index_notes kg_index_notes Read kg_memory_connections kg_memory_connections Read kg_paths kg_paths Read library_coverage library_coverage Read list_background_packs List the knowledge background packs available to install, and what is already installed. Read list_backups List all backup files with size, age, and checksum availability. Read list_basket List files in the Metis basket (legacy & inspiration documents). Read list_brainstorm_sessions List recent brainstorm sessions with title, turn count, and status. Read list_contexts List all user contexts (general + specialist) with active status. Read list_data_triggers List all data automation triggers with their status. Read list_folder List files in a folder. Read list_generated_images List recently generated images in the PKM. Read list_knowledge_databases List all knowledge databases (layers) registered in Metis. Read list_outputs List what Metis has produced, newest first. Read list_recent_memory Return the n most recent memory entries (default 10). Read list_recent_sessions list_recent_sessions Read list_research_entities List all entities in the research timeline with their claim count and last update. Read list_supported_formats List supported dataset formats and installed library versions. Read list_tool_groups List the tool groups that can be loaded on demand, with how many are parked. Read load_project_context load_project_context Read load_tool_group Load every tool in a named group at once (see list_tool_groups for names). Read log_span log_span Read metis_doctor metis_doctor Read mine_references mine_references Read nature_briefing The latest Nature Briefing edition, as text. Read next_discovery_tip next_discovery_tip Read preview_focus_lens preview_focus_lens Read probe_tool_result probe_tool_result Read profile_dataset profile_dataset Read propose_skill_improvement propose_skill_improvement Read query_research_timeline query_research_timeline Read read_file read_file Read read_office_document read_office_document Read reading_stack_show What is in the reading stack: saved, later, declined or read. Read recall recall Read recall_decisions recall_decisions Read record_persona_learning record_persona_learning Read record_thinking_event record_thinking_event Read record_viz_use record_viz_use Read redact_data_file redact_data_file Read reindex_memory reindex_memory Read remember remember Read review_course review_course Read scan_folder_for_intent scan_folder_for_intent Read scan_inbox scan_inbox Read scan_library scan_library Read scan_nature_briefings Fetch the latest Nature Briefing editions from the public archive feed. Read scan_news scan_news Read scan_openalex scan_openalex Read scan_outgoing scan_outgoing Read scan_project_folder Scan a project folder to detect work done since last scan. Read scan_pubmed_alerts scan_pubmed_alerts Read scan_tracked_files Scan all tracked files and report which have changed since last scan. Read search_code_repository search_code_repository Read search_fulltext search_fulltext Read search_library search_library Read search_literature search_literature Read search_literature_extended search_literature_extended Read search_memory search_memory Read search_notes search_notes Read search_pdf_knowledge search_pdf_knowledge Read search_semantic_scholar search_semantic_scholar Read search_session_memory search_session_memory Read semantic_search semantic_search Read session_bootstrap session_bootstrap Read show_agent_decisions show_agent_decisions Read show_focus_areas List every focus area, its state, and what it currently holds. Read suggest_cleaning suggest_cleaning Read suggest_interests_from_work suggest_interests_from_work Read surface_relevant_context surface_relevant_context Read transcribe_recording transcribe_recording Read transcribe_voice transcribe_voice Read validate_pipeline_stage validate_pipeline_stage Read verify_backup Run SQLite integrity_check on a backup file. Read verify_claim verify_claim Read verify_doi verify_doi Read verify_text_citations verify_text_citations Read viz_library_overview viz_library_overview Read weigh_evidence weigh_evidence

OTHER 3 tools

Other brainstorm_turn brainstorm_turn Other end_span end_span Other start_span start_span

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Metis Public Health

Can an AI agent delete data through the Metis Public Health MCP server? +

Yes. The Metis Public Health server exposes 9 destructive tools including archive_library_item, delete_data_trigger, delete_knowledge_database. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Metis Public Health? +

The Metis Public Health server has 98 write tools including add_glossary_term, add_journal_entry, add_memory_entry. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Metis Public Health.

How many tools does the Metis Public Health MCP server expose? +

277 tools across 4 categories: Destructive, Execute, Read, Write. 156 are read-only. 121 can modify, create, or delete data.

How do I enforce a policy on Metis Public Health? +

Register the Metis Public Health MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Metis Public Health tool call.

Deterministic rules across all 277 Metis Public Health tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON METIS PUBLIC HEALTH →

Instant setup, no code required.

277 Metis Public Health tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Metis Public Health's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →