atomadic 0.2.3

Atomadic Python SDK -- one MCP, entitlement-gated tool-sets

Atomadic Python SDK

One MCP. One key. Every tool-set you are entitled to.

Atomadic is sovereign infrastructure for the agent economy. Mount one MCP at mcp.atomadic.tech; your entitlement key decides which product tool-sets you can call. Every call passes Gate-1 (entitlement) then Gate-2 (trust).

• Docs: https://atomadic.tech/docs.html
• Architecture: https://atomadic.tech/docs.html?d=architecture
• Support: [e-mail]

Install

pip install atomadic

Quickstart

from atomadic import Atomadic, fuse

ato = Atomadic(api_key='ato_...')  # or set ATOMADIC_KEY env var

# Call any tool your plan unlocks:
result = fuse.assess_architecture_pure(
    ato,
    source_text='def f(x):\n    return x + 1',
    module_name='f_pure',
)
print(result['verdict'], result['density'])

# Or browse the surface your key unlocks:
for t in ato.list_tools():
    print(t['name'])

Authentication

Get an entitlement key from atomadic.tech. The key is decoded and verified at the edge on every call; minting is internal-only. Keep keys server-side -- the gate refuses out-of-plan calls, but secrets belong in your env.

ato = Atomadic(api_key='ato_<blob>_<sig>')
# or:  export ATOMADIC_KEY=ato_<blob>_<sig>

Products & tool-sets

Each product is an entitlement-gated tool-set; hold the entitlement, call the tool. Reserved products (Vanguard, Aegis, Catalyst) and roadmap (Evolve, Research, Mind-Lab) are not yet in the SDK.

Fuse [live]

entitlement: fuse · from atomadic import fuse

Architecture compiler -- AI writes code, we give it architecture.

Analyze your code against the 5-tier, single-callable discipline.

Tool	Required args
assess_architecture_pure	source_text, module_name
assess_import_direction_pure	source_text, tier
orchestrate_s2s_temporal	intent
scan_code_stubs_pure	source_text

from atomadic import Atomadic, fuse
ato = Atomadic(api_key='ato_...')
fuse.assess_architecture_pure(ato, source_text=..., module_name=...)

See per-tool docstrings for full arg schemas: help(fuse.assess_architecture_pure)

Nexus [live]

entitlement: nexus · from atomadic import nexus

The trust gate every action passes.

Gate-2 sovereign trust: trust phases, hallucination bound, signed attestations.

Tool	Required args
assess_nexus_trust_phase_stateful	ledger_path
define_nexus_constants_pure	(none)
enforce_nexus_gate_stateful	action_kind, severity
record_nexus_attestation_stateful	action_kind, severity, ledger_path
record_nexus_escalation_stateful	action_kind, escalation_path
scan_nexus_attestation_history_stateful	ledger_path

from atomadic import Atomadic, nexus
ato = Atomadic(api_key='ato_...')
nexus.assess_nexus_trust_phase_stateful(ato, ledger_path=...)

See per-tool docstrings for full arg schemas: help(nexus.assess_nexus_trust_phase_stateful)

Security [live]

entitlement: security · from atomadic import security

A bubble of protection around every agent.

Bubble check, redaction, error-fold, hardening posture (PQC/FIPS-203).

Tool	Required args
assess_security_bubble_pure	content
classify_error_fold_pure	error_message
compute_hardening_posture_pure	target_product_id, hardening_level
compute_redacted_args_pure	args
compute_redacted_text_pure	text
define_security_constants_pure	(none)

from atomadic import Atomadic, security
ato = Atomadic(api_key='ato_...')
security.assess_security_bubble_pure(ato, content=...)

See per-tool docstrings for full arg schemas: help(security.assess_security_bubble_pure)

Proving Ground [live]

entitlement: proving · from atomadic import proving

Nothing ships unproven.

Ship-gate, proof-readiness signals, and test-coverage estimation.

Tool	Required args
assess_proof_readiness_pure	source_text
assess_test_quality_pure	test_source
compute_proof_obligations_pure	source_text
score_documentation_coverage_pure	source_text
score_test_coverage_pure	source_text, test_source

from atomadic import Atomadic, proving
ato = Atomadic(api_key='ato_...')
proving.assess_proof_readiness_pure(ato, source_text=...)

See per-tool docstrings for full arg schemas: help(proving.assess_proof_readiness_pure)

Release [live]

entitlement: release · from atomadic import release

Template -> render -> deploy.

Template registry, website render, Cloudflare deploy. Dry-run by default.

Tool	Required args
record_release_template_stateful	template_id, kind, source_kind, source_ref, registry_path
render_from_template_pure	template, context
render_website_stateful	template_dir, context, output_dir
scan_release_templates_stateful	registry_path
serve_cloudflare_pages_stateful	directory, project_name
serve_cloudflare_worker_stateful	worker_dir

from atomadic import Atomadic, release
ato = Atomadic(api_key='ato_...')
release.record_release_template_stateful(ato, template_id=..., kind=..., source_kind=...)

See per-tool docstrings for full arg schemas: help(release.record_release_template_stateful)

Healer [beta]

entitlement: healer · from atomadic import healer

Diagnose, grade, and plan the repair.

Read-only diagnosis: code-health grade + advisory repair plan.

Tool	Required args
assess_artifact_health_pure	source_text
classify_failure_mode_pure	error_message
compose_rollback_plan_pure	error_message
compute_blast_radius_pure	source_text, symbol
compute_repair_plan_pure	error_message

from atomadic import Atomadic, healer
ato = Atomadic(api_key='ato_...')
healer.assess_artifact_health_pure(ato, source_text=...)

See per-tool docstrings for full arg schemas: help(healer.assess_artifact_health_pure)

Mind_Lab

entitlement: mind_lab · from atomadic import mind_lab

Tool	Required args
assess_falsifiability_pure	claim
assess_proposal_verdict_pure	proposal_text
compose_adversarial_critique_pure	proposal

from atomadic import Atomadic, mind_lab
ato = Atomadic(api_key='ato_...')
mind_lab.assess_falsifiability_pure(ato, claim=...)

See per-tool docstrings for full arg schemas: help(mind_lab.assess_falsifiability_pure)

Evolve

entitlement: evolve · from atomadic import evolve

Tool	Required args
assess_improvement_candidates_pure	source_text, module_name
assess_regression_risk_pure	source_text
score_evolution_fitness_pure	before_source, after_source

from atomadic import Atomadic, evolve
ato = Atomadic(api_key='ato_...')
evolve.assess_improvement_candidates_pure(ato, source_text=..., module_name=...)

See per-tool docstrings for full arg schemas: help(evolve.assess_improvement_candidates_pure)

Research

entitlement: research · from atomadic import research

Tool	Required args
compose_experiment_design_pure	hypothesis
compose_problem_decomposition_pure	problem
compose_research_panel_pure	question

from atomadic import Atomadic, research
ato = Atomadic(api_key='ato_...')
research.compose_experiment_design_pure(ato, hypothesis=...)

See per-tool docstrings for full arg schemas: help(research.compose_experiment_design_pure)

Two-gate dispatch

Every call is filtered then verified:

1. Gate-1 (entitlement): tools/list shows only the tools your plan unlocks; out-of-plan tools/call is refused.
2. Gate-2 (trust, Nexus): trust phase + severity ceiling + hallucination bound. Governed actions return a signed attest:<id> receipt.

See the architecture docs for the full model.

Plans

Free / Basic / Dev / Pro / Teams / Enterprise -- per product, or whole-line via Murmuration Complete. Subscription is the product; x402 meters only overage + agent- to-agent calls. Pricing: https://atomadic.tech/docs.html?d=pricing.

Determinism

Pure-tier tools have no side effects and no hidden state: same inputs, same output, same content hash, every time. Re-running a pure tool is a verification.

Contributing

This SDK is auto-emitted from the live Atomadic MCP registry -- changes here should flow through the engine, not be hand-patched. For issues, requests, or feedback: [e-mail].

License

Apache-2.0 -- see LICENSE.