Atlas entry

`ailawframework.com`

35 capabilities over MCP. The inventory is incomplete. First atlas observation.

Observed 12 Nov 2026, 02:46 UTC · passive: no tools called, no credentials sent · sha256:738451…9976

35 capabilities, 19 of them tools. 9 only read. 1 only computes. 1 reading is disputed. 8 have no reading.

AI reading, beta. side-effects v1 on claude-haiku-5.5, calibrated on MCP (golden-3). Only readings above a measured precision count. Counts are tools, not calls: no tool was called.

AI readings summary · beta

The service lists 19 tools, and 10 have AI readings.

9 tools are read as read-only, including get_framework, get_software_profile and search_library.

assess_and_decide: Assesses an AI option against a manual route on adoption, efficiency and governance, then returns a decision with reasons.

disclosure_duties: Returns recorded filing-disclosure and certification requirements for a court forum and document type, read from stored rules.

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

What an agent can do here

AI readings, beta · Readings on 11 of 19 MCP tools.

Moves money
0
No tool read this way.
Deletes or cancels records
0
No tool read this way.
Sends messages to people
0
No tool read this way.
Changes permissions
0
No tool read this way.
Runs code
0
No tool read this way.
Should ask a person first
0
No tool read this way.

No counted reading 8 tools No reading was counted, so any effect above is possible for them: assess_tool_use, disclosure_duties, get_started, plan_human_work, record_answers, refine_legal_query, start_task, work_record.

What changed

First atlas observation. Atlas history

Look first

AI reading, beta: AI adds items here; it never removes one.

record_researchA fact disputes the reading

Surfaces

5 protocols checked

ARD	Not found	No document retrieved
A2A	Not found	0 skills
MCP	Valid	2025-11-25 · 19 tools · 16 resources · 0 prompts retained · listing incomplete
OpenAPI	Not detected	0 operations
WebMCP	Not detected	0 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 2025-11-25 · 19 tools · 16 resources · 0 prompts retained · listing incomplete
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

35 · inventory incomplete

Showing 35 of 35.

Tool and inputs							◇ AI reading, beta · confidence
Read as one of the six effects 1 AI only raises attention: these rows come first.
findings, record							Disputed by a fact
`record_research` inputs `findings` (required), `record` (required) AI · beta · disputed The model read this as creates records (0.80). The Declared readOnlyHint `true` disagrees. Treated as unknown.
Read as none of the six 10 Not a clearance.
◇ AI Assesses an AI option against a manual route on adoption, efficiency and governance, then returns a decision with reasons.adoption, conditions, efficiency, efficiency_confidence and 4 more							Computes only, changes nothing0.84
`assess_and_decide` inputs `adoption` (required), `conditions`, `efficiency` (required), `efficiency_confidence` and 4 more AI Computes only, changes nothing 0.84
federal_court, forum, judge, jurisdiction and 1 more							Reads only0.86
`find_rules` inputs `federal_court`, `forum`, `judge`, `jurisdiction` and 1 more AI Reads only 0.86
◇ AI Returns the rules of an AI governance framework, optionally filtered to steps, pillars, decision logic, levels, stages or absolute rules.part							Reads only0.88
`get_framework` inputs `part` AI Reads only 0.88
audience, court, document_type, forum and 3 more							Reads only0.88
`get_jurisdiction_guidance` inputs `audience`, `court`, `document_type`, `forum` and 3 more AI Reads only 0.88
area*, jurisdiction							Reads only0.90
`get_practice_area_prompt` inputs `area` (required), `jurisdiction` AI Reads only 0.90
precedent_id*							Reads only0.92
`get_precedent` inputs `precedent_id` (required) AI Reads only 0.92
◇ AI Returns a governance profile for one AI product or plan, with its facts, considerations and dated sources, looked up by id or name.controls, product*							Reads only0.85
`get_software_profile` inputs `controls`, `product` (required) AI Reads only 0.85
jurisdiction, task_id*							Reads only0.90
`get_task_guidance` inputs `jurisdiction`, `task_id` (required) AI Reads only 0.90
kind, limit, query*							Reads only0.90
`search_library` inputs `kind`, `limit`, `query` (required) AI Reads only 0.90
area, limit, query*							Reads only0.90
`search_precedents` inputs `area`, `limit`, `query` (required) AI Reads only 0.90
No counted reading 8 No reading was counted, so any effect is possible.
forum, jurisdiction, task, tool	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`assess_tool_use` inputs `forum`, `jurisdiction`, `task` (required), `tool` (required)
◇ AI Returns recorded filing-disclosure and certification requirements for a court forum and document type, read from stored rules.document, federal_court, forum, judge and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`disclosure_duties` inputs `document` (required), `federal_court`, `forum` (required), `judge` and 1 more
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`get_started`
record*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`plan_human_work` inputs `record` (required)
answers*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`record_answers` inputs `answers` (required)
area, query*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`refine_legal_query` inputs `area`, `query` (required)
agent, answers	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`start_task` inputs `agent`, `answers`
agent_did, check_points, lawyer_checkpoints, notes and 2 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`work_record` inputs `agent_did`, `check_points`, `lawyer_checkpoints`, `notes` and 2 more
MCP resources 16 Not read by AI.
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`
no inputs							Not read
`name not shown`

Read as this effect No reading: unknown Not read as this effect◇ AI readings, beta. A zero is a count, not a clearance.

MCP prompts 0+ observed

Inventory incomplete. The displayed count is a lower bound; missing items do not prove removal.

None recorded in this Passport.

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

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.

The comparison with the previous observation is shown only to the account that recorded it.

Atlas history

1 observation

12 Nov 2026, 02:46 UTC35 capabilities · MCP 2025-11-25 · MCP endpoint truncated · 1 incomplete inventory groupFirst observation
Fingerprint and versions
Fingerprint
738451651cf640331cb7ef4457be30540616904cc300b445d6af30c1b9139976 (incomplete)
Passport schema
0.5.0, passport-semantic-v4
Consistency
MCP_PROMPTS_ADVERTISEMENT_LIST: indeterminate · MCP_RESOURCES_ADVERTISEMENT_LIST: match · 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.

Declared and observed

record_research
Declared
The publisher declares it read-only.
Read
AI · beta The AI reading: creates records (0.8).

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

About this entry

com.ailawframework/ai-law-framework
Listed
Official MCP Registry · first listed 2 Nov 2026 · last listed 2 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: sha256:5fda52aa5d64050256cbbff64c4e017133e4b397b6161b164a20f4e40301bbaf
Locator SHA-256: 8cbd6f6962123044e1fe009ca4abdf09a735dd0c242ffb9cc445a531e0cdadac
Snapshot generated: 12 Nov 2026, 05:07 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.

Capability facts

As observed from outside, at the time below

Observed: 12 Nov 2026, 02:46 UTC
Signed: 12 Nov 2026, 05:07 UTC

Protocols: MCP
Tools: 19
Declared sign-in: None declared

Effects counted AI readings, beta

Moves money: 0
Deletes or cancels records: 0
Sends messages to people: 0
Changes permissions: 0
Runs code: 0
Asks a person: 0

19 tools examined; 10 counted above a measured threshold; 1 disputed.

Declared vs read disagreements

Declared read-only, read as writing: 1
Declared destructive, read as not writing: 0
Declared non-destructive, read as deleting: 0
Declared closed-world, read as reaching out: 0

Change since previous: First observation
Label status: Current