Atlas entry

mcp.zerotrustphysics.com

18 capabilities over MCP. First atlas observation.

Observed · passive: no tools called, no credentials sent · sha256:b86b98…e626

Surfaces

5 protocols checked

ARDNot foundNo document retrieved
A2ANot found0 skills
MCPValid2026-07-28 · 18 tools · resources not advertised · prompts not advertised
OpenAPINot detected0 operations
WebMCPNot detected0 declarative form tools · experimental
Exact states and meaning
  • ARD
    absent

    Exact state: not found · No document retrieved

    The supported discovery location returned no matching document.

    Not found does not prove the service exposes no such interface elsewhere.

    Not observed / not fetched

  • A2A
    absent

    Exact state: not found · 0 skills

    The supported discovery location returned no matching document.

    Not found does not prove the service exposes no such interface elsewhere.

    Not observed / not fetched

  • MCP
    observed

    Exact state: valid · Revision 2026-07-28 · 18 tools · resources not advertised · prompts not advertised

    A usable protocol document was retrieved and validated.

    Directly observed

  • OpenAPI
    absent

    Exact state: not detected · 0 operations

    No endpoint was established from the evidence and scope that InterfaceDelta inspected.

    Not detected does not prove that no endpoint exists.

    Not observed / not fetched

  • WebMCP
    absent

    Exact state: not detected · 0 declarative form tools · experimental

    No named declarative WebMCP form tools were observed in the origin root HTML.

    Script-registered tools and other pages are not observed, so this does not mean the site has no WebMCP tools.

    Not observed / not fetched

Capabilities

18 · inventory complete

Summary of the AI readings · beta

The service lists 18 capabilities, and 4 have AI readings.

describe_card, list_solvers and list_cards are read as read-only.

Rows named: describe_card · list_solvers · list_cards

Written by code from the AI readings on this page: it groups them and says nothing they do not.

The atlas shows each capability by its plain identifier, inputs and declared sign-in. Publisher descriptions, paths, links and source evidence are not published here.

MCP tools 18

  • cite

    inputs card, domain, solver

    AI Computes only, changes nothing 0.80

  • compute_step

    inputs card (required), domain (required), from, parameters (required)

  • describe_card

    inputs card (required), domain (required), form

    AI Reads only 0.82

  • describe_solver

    inputs form, part, solver (required)

  • design_run

    inputs request (required), target (required), vary (required)

  • find_flip

    inputs high (required), level, low (required), request (required) and 1 more

  • find_model

    inputs description (required), limit

  • list_cards

    AI Reads only 0.90

  • list_solvers

    AI Reads only 0.85

  • run_dataset

    inputs answer, card, domain, plan (required) and 3 more

  • run_trajectory

    inputs card (required), domain (required), dt_s (required), from and 4 more

  • solve

    inputs example, from, parameters, solver (required)

  • validate_series

    inputs commitment, component, measurements (required), quantity (required) and 2 more

  • verify_dataset

    inputs dataset_seal, frames_hex, head, public_key and 3 more

  • verify_receipt

    inputs public_key, response_text (required), seen_nonces

  • verify_solution

    inputs engine_version, field_sha384, from, inputs and 10 more

  • verify_step

    inputs card (required), domain (required), from, parameters (required)

  • verify_tape

    inputs chain_seal, final_residual_conservation_error_hex, final_state, frames and 11 more

Not observed in this Passport: A2A skills, MCP resources, MCP prompts, OpenAPI operations.

Declared and observed

18 tools declare hints; the AI readings agree with all 4 that have a reading.

A disagreement is not a finding about the service: either side can be wrong. How we compare declarations and readings.

Atlas history

1 observation

  • 18 capabilities · MCP 2026-07-28 · MCP endpoint validFirst observation
    Fingerprint and versions
    Fingerprint
    b86b98263b22ca6d991187b5d8e419e5dce4cb7585562ee3e91255b467c4e626
    Passport schema
    0.5.0, passport-semantic-v4
    Consistency
    MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable

Each class compares an observation with the previous atlas observation. Runs of unchanged observations are grouped. Struck values are what the previous observation recorded; inserted values are what this one recorded.

About this entry

  • com.zerotrustphysics/verifier
    Listed

    Official MCP Registry · first listed 3 Nov 2026 · last listed 3 Nov 2026

Passive observations of a public interface listed in the Official MCP Registry. An observation does not verify security, ownership or compliance, and InterfaceDelta assigns no scores or rankings. Methodology · Report an inaccuracy · Ask for removal

Identity and snapshot
Target key
sha256:f86d69feb1ea373799f13629b18a92748b96ee100c0512f12a37c26377ca2bdf
Locator SHA-256
e7d6413774ec51dee9ee7ec32c0edab0b43e0152a9b3f39ef761c2e89b4f21ce
Snapshot generated
4 Nov 2026, 00:59 UTC

The entry is one exact observed target, not a real-world service identity, and implies no ownership. Endpoint paths are not published; the locator hash lets an operator confirm their own URL.