Atlas entry

`forge.atomadic.tech`

68 capabilities over MCP. First atlas observation.

Observed 6 Nov 2026, 02:04 UTC · passive: no tools called, no credentials sent · sha256:1b7f5a…97f3

68 tools. 13 only read. 8 only compute. 3 change records. 1 moves money. 43 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 68 tools, and 23 have AI readings.

escrow_release is read as moving money.

compliance_incident, escrow_create and agents_register are read as creating records.

11 tools are read as read-only, including forge_leaderboard, compliance_incidents and trust_decay.

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 25 of 68 MCP tools. 1 reads as moving money.

Moves money
1 tool
- escrow_release0.82
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 43 tools No reading was counted, so any effect above is possible for them: agents_contradiction, agents_intent_classify, agents_plan, agents_semantic_diff, compliance_check, compliance_eu_ai_act, compliance_explain, compliance_fairness, compliance_lineage, compliance_oversight and 33 more.

What changed

First atlas observation. Atlas history

Look first

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

escrow_releaseMoves money · 0.82

Surfaces

5 protocols checked

ARD	Not found	No document retrieved
A2A	Not found	0 skills
MCP	Valid	2024-11-05 · 68 tools · resources not advertised · prompts not advertised
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 2024-11-05 · 68 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

68 · inventory complete

Showing 68 of 68.

Tool and inputs							◇ AI reading, beta · confidence
Read as one of the six effects 1 AI only raises attention: these rows come first.
escrow_id*◇ AIMoves money 0.82	Moves money 0.82						Moves money0.82
`escrow_release` inputs `escrow_id` (required) AI Moves money 0.82
Read as none of the six 24 Not a clearance.
agent_id, capabilities							Creates records0.83
`agents_register` inputs `agent_id` (required), `capabilities` (required) AI Creates records 0.83
agent_id*							Reads only0.85
`agents_reputation` inputs `agent_id` (required) AI Reads only 0.85
no inputs							Reads only0.84
`agents_topology` AI Reads only 0.84
claimed_digest, inputs*							Computes only, changes nothing0.81
`audit_work_claim` inputs `claimed_digest`, `inputs` (required) AI Computes only, changes nothing 0.81
affected_users, description, severity, system_id							Creates records0.80
`compliance_incident` inputs `affected_users` (required), `description` (required), `severity` (required), `system_id` (required) AI Creates records 0.80
system_id*							Reads only0.80
`compliance_incidents` inputs `system_id` (required) AI Reads only 0.80
system_id*							Reads only0.88
`compliance_oversight_history` inputs `system_id` (required) AI Reads only 0.88
include, period, system_id*							Reads only0.85
`compliance_transparency` inputs `include` (required), `period` (required), `system_id` (required) AI Reads only 0.85
contract_id, contract_type							Reads only0.80
`defi_contract_audit` inputs `contract_id` (required), `contract_type` (required) AI Reads only 0.80
claims*							Computes only, changes nothing0.86
`detect_contradiction` inputs `claims` (required) AI Computes only, changes nothing 0.86
amount, conditions, currency, payee_id* and 1 more							Creates records0.80
`escrow_create` inputs `amount` (required), `conditions`, `currency` (required), `payee_id` (required) and 1 more AI Creates records 0.80
no inputs							Reads only0.85
`forge_leaderboard` AI Reads only 0.85
agent_id*							Reads only0.80
`identity_verify` inputs `agent_id` (required) AI Reads only 0.80
receipts*							Computes only, changes nothing0.80
`receipt_reputation` inputs `receipts` (required) AI Computes only, changes nothing 0.80
atom_name, language, source_text							Computes only, changes nothing0.82
`render_polyglot_roundtrip_pure` inputs `atom_name` (required), `language`, `source_text` (required) AI Computes only, changes nothing 0.82
no inputs							Computes only, changes nothing0.88
`rng_quantum` AI Computes only, changes nothing 0.88
no inputs							Reads only0.80
`rng_verify` AI Reads only 0.80
no inputs							Reads only0.84
`swarm_inbox` AI Reads only 0.84
max_keywords, text*							Computes only, changes nothing0.82
`text_keywords` inputs `max_keywords`, `text` (required) AI Computes only, changes nothing 0.82
text*							Computes only, changes nothing0.82
`text_sentiment` inputs `text` (required) AI Computes only, changes nothing 0.82
text*							Computes only, changes nothing0.80
`text_summarize` inputs `text` (required) AI Computes only, changes nothing 0.80
no inputs							Reads only0.81
`trust_decay` AI Reads only 0.81
agent_id*							Reads only0.85
`trust_history` inputs `agent_id` (required) AI Reads only 0.85
agent_id*							Reads only0.86
`trust_score` inputs `agent_id` (required) AI Reads only 0.86
No counted reading 43 No reading was counted, so any effect is possible.
statements*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`agents_contradiction` inputs `statements` (required)
text*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`agents_intent_classify` inputs `text` (required)
constraints, goal*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`agents_plan` inputs `constraints`, `goal` (required)
context, output_a, output_b	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`agents_semantic_diff` inputs `context`, `output_a` (required), `output_b` (required)
chain_depth, description, kl_divergence	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`compliance_check` inputs `chain_depth`, `description`, `kl_divergence`
intended_purpose, risk_category, system_id*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`compliance_eu_ai_act` inputs `intended_purpose` (required), `risk_category` (required), `system_id` (required)
decision_id, model_id, subject_context*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`compliance_explain` inputs `decision_id` (required), `model_id` (required), `subject_context` (required)
dataset_id, metric, model_id, protected_attrs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`compliance_fairness` inputs `dataset_id` (required), `metric` (required), `model_id` (required), `protected_attrs` (required)
dataset_stages, model_id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`compliance_lineage` inputs `dataset_stages` (required), `model_id` (required)
decision, notes, reviewer_id, system_id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`compliance_oversight` inputs `decision` (required), `notes` (required), `reviewer_id` (required), `system_id` (required)
amount, bridge_id, dest_chain, source_chain and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`defi_bridge_verify` inputs `amount` (required), `bridge_id` (required), `dest_chain` (required), `source_chain` (required) and 1 more
collateral_factor, collateral_value, debt_value, position_id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`defi_liquidation_check` inputs `collateral_factor` (required), `collateral_value` (required), `debt_value` (required), `position_id` (required)
position, protocol, risk_tolerance*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`defi_optimize` inputs `position` (required), `protocol` (required), `risk_tolerance` (required)
asset, oracle_address, price_feed, reference_price and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`defi_oracle_verify` inputs `asset` (required), `oracle_address` (required), `price_feed` (required), `reference_price` (required) and 1 more
market_conditions, position, protocol*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`defi_risk_score` inputs `market_conditions` (required), `position` (required), `protocol` (required)
principal_usd, risk_tolerance	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`defi_yield_optimize` inputs `principal_usd` (required), `risk_tolerance` (required)
id*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`drift_certificate` inputs `id` (required)
current_window, model_id, reference_window*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`drift_check` inputs `current_window` (required), `model_id` (required), `reference_window` (required)
claimed_digest, inputs*, obligation	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`enforce_sla` inputs `claimed_digest`, `inputs` (required), `obligation`
escrow_id, evidence, reason	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`escrow_dispute` inputs `escrow_id` (required), `evidence`, `reason` (required)
model*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`forge_badge` inputs `model` (required)
delta, description, model_id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`forge_delta_submit` inputs `delta` (required), `description`, `model_id` (required)
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`forge_quarantine`
model_id*, verification_type	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`forge_verify` inputs `model_id` (required), `verification_type`
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`identity_sybil_check`
messages*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`inference` inputs `messages` (required)
messages*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`inference_stream` inputs `messages` (required)
agent_id	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`murmuration` inputs `agent_id`
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`oracle_entropy`
claim*, context	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`oracle_hallucination` inputs `claim` (required), `context`
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`rag_augment`
session_id*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ratchet_advance` inputs `session_id` (required)
no inputs	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ratchet_probe`
session_id*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`ratchet_register` inputs `session_id` (required)
atom_name, source_text	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`render_polyglot_all_pure` inputs `atom_name` (required), `source_text` (required)
agent_id, counterparty_id, interaction_type, outcome*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`reputation_record` inputs `agent_id` (required), `counterparty_id`, `interaction_type` (required), `outcome` (required)
intent*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`route_capability` inputs `intent` (required)
context, target*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`security_zero_day` inputs `context`, `target` (required)
consumer_id, provider_id, terms*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`sla_register` inputs `consumer_id` (required), `provider_id` (required), `terms` (required)
description, sla_id, violation_type	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`sla_report` inputs `description`, `sla_id` (required), `violation_type` (required)
message, target_agent_id, ttl	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`swarm_relay` inputs `message` (required), `target_agent_id` (required), `ttl`
agent_id*, context	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`threat_score` inputs `agent_id` (required), `context`
claimed_digest, inputs*	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`verify_settlement` inputs `claimed_digest`, `inputs` (required)

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

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

6 Nov 2026, 02:04 UTC68 capabilities · MCP 2024-11-05 · MCP endpoint validFirst observation
Fingerprint and versions
Fingerprint
1b7f5aa3197071ffbcfd1e151bfb7c91e5809b2ea4b722d425cf09d37a3097f3
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.

Declared and observed

68 tools declare hints; the AI readings agree with all 25 that have a reading.

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

About this entry

io.github.atomadictech/atomadic-forge
Deprecated
Official MCP Registry · first listed 6 Nov 2026 · last listed 6 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: sha256:30b862b29a2a750bf1e6ed34b430f555c712a34dabbd6601f838517c127d861c
Locator SHA-256: cca86d7a64d5e903f825d4678bc63bf5a73a66829bf55a8fb1221734a11e3c83
Snapshot generated: 11 Nov 2026, 22:36 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: 6 Nov 2026, 02:04 UTC
Signed: 6 Nov 2026, 03:03 UTC

Protocols: MCP
Tools: 68
Declared sign-in: None declared

Effects counted AI readings, beta

Moves money: 1
Deletes or cancels records: 0
Sends messages to people: 0
Changes permissions: 0
Runs code: 0
Asks a person: 0

68 tools examined; 25 counted above a measured threshold.

Declared vs read disagreements

Declared read-only, read as writing: 0
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