// SCAN REPORT

Adia Ai

43 tools. 9 can modify or destroy data without limits.

8 write tools that can modify data. Rate limits recommended.

Last updated: 19 Aug 2026

9 can modify or destroy data

34 read-only

43 tools total

Community server · catalogue entry checked 19/08/2026

How to control Adia Ai ↓

TOOL MAP

What Adia Ai exposes to your agents

Read (34) Write / Execute (8) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Adia Ai tools

Execute · Medium run_eval Run the offline eval harness against the held-out intent set. Returns aggregate scores and per-intent results. Write · Medium scaffold_component Based on the server description which explicitly lists 'scaffolding' as a key capability, 'scaffold_component' most likely generates and writes boilerplate/template files for a new strategy component. Write · Medium report_issue File a structured issue ticket \u2014 writes BOTH a machine-readable JSON file AND a human-readable Markdown report containing the full sess Write · Medium convert_html Convert HTML markup to A2UI flat adjacency component messages. Maps HTML tags to AdiaUI components, infers layout from styles, enforces Card

9 of Adia Ai's 43 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Adia Ai

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

Rate limit write operations

{
  "convert_html": {
    "limits": [
      {
        "counter": "convert_html_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "assemble_context": {
    "limits": [
      {
        "counter": "assemble_context_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 Adia Ai — 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 ADIA AI →

Instant setup, no code required.

FULL CATALOGUE

All 43 Adia Ai tools

EXECUTE 1 tools

Execute run_eval Run the offline eval harness against the held-out intent set. Returns aggregate scores and per-intent results.

WRITE 7 tools

Write convert_html Convert HTML markup to A2UI flat adjacency component messages. Maps HTML tags to AdiaUI components, infers lay Write generate_ui Generate A2UI components from a natural language description. Engine selection: - Write plan_app_state Analyze a natural language prompt and extract the top-level Generative UI Ontology structures (Intent, Domain, Write refine_composition Refine an existing chunk-composed UI based on a natural-language intent or an explicit op-list. Use when the Write report_issue File a structured issue ticket \u2014 writes BOTH a machine-readable JSON file AND a human-readable Markdown r Write resolve_composition Return the flat A2UI template + updateComponents messages for a composition. Zettel-only. (Pre-inlined since \ Write scaffold_component scaffold_component

READ 34 tools

Read assemble_context Assemble progressive-disclosure context for a given intent and budget tier. Returns domain-relevant components Read audit_structure audit_structure Read check_anti_patterns Check HTML against all anti-patterns. Returns only violations. Read classify_intent Classify intent into a UI domain. Read compose_from_chunks Compose a UI page from training chunks \u2014 retrieval-first, synthesis-fallback. Mix-and-match composition Read factory_status factory_status Read get_catalog_ladder get_catalog_ladder Read get_catalog_tiers get_catalog_tiers Read get_chunk get_chunk Read get_component_map Get the full AdiaUI component catalog. Read get_composition Fetch a composition by name. Returns the flat A2UI template (compositions are pre-inlined; no $fragment refs). Read get_graph Return the composition catalog. Zettel-only. (Backlinks to fragments retired in \xA737; only composition nodes Read get_quality_metrics get_quality_metrics Read get_registry_map get_registry_map Read get_state Inspect a cached composition state by state_id. Returns the full cache entry including the materialized HTML, Read get_training_gaps get_training_gaps Read get_traits Get the trait catalog, optionally filtered by category. Read get_wiring_catalog Get the AdiaUI wiring catalog: available controllers, action handlers, refresh strategies, value sources, and Read get_wiring_registry get_wiring_registry Read list_patterns List all composition patterns in the A2UI corpus. Optional filters narrow by domain (auth, settings, dashboard Read lookup_chunk lookup_chunk Read lookup_component Look up a AdiaUI component by type name. Read orient_app orient_app Read protocol_status protocol_status Read refine_ui refine_ui Read scaffold_app scaffold_app Read scaffold_page scaffold_page Read search_chunks search_chunks Read search_patterns Search the composition library for reusable UI templates. Returns matching compositions with full A2UI compone Read server_status Returns operational status of the MCP server: transport, sampling capability, corpus stats, version. Read validate_document validate_document Read validate_schema Validate A2UI messages against schema rules. Read verify_surface verify_surface Read zettel_stats Zettel corpus stats \u2014 composition count + average node count. (Fragment stats retired in \xA737.)

OTHER 1 tools

Other submit_feedback submit_feedback

EXPLORE

Related servers

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

FAQ

Questions about Adia Ai

How do I prevent bulk modifications through Adia Ai? +

The Adia Ai server has 7 write tools including convert_html, generate_ui, plan_app_state. 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 Adia Ai.

How many tools does the Adia Ai MCP server expose? +

43 tools across 3 categories: Execute, Read, Write. 34 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on Adia Ai? +

Register the Adia Ai 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 Adia Ai tool call.

Deterministic rules across all 43 Adia Ai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ADIA AI →

Instant setup, no code required.

43 Adia Ai tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Adia Ai'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 →