Name: a2a2p — Agent-to-Agent-to-Physical
Author: a2a2p

a2a2p — Agent-to-Agent-to-Physical MCP

Turn agent intent into physical parts: engineering review, measured geometry, calibrated pricing.

not scanned Remote · Streamable HTTP No auth needed 28 tools v1.6.0

No reviews yet by a2a2p The publisher’s own endpoint — this marketplace is not in the path

tools declared

—

trust score

remote

at its publisher

—

calls last 7d

What it does

Turn agent intent into physical parts: engineering review, measured geometry, calibrated pricing.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http a2a2p-agent-to-agent-to-physical-mcp https://a2a2p.com/mcp

# 2 — ask your agent for something these tools do
#   request_physical_solution, review_specification, qualify_specification_exchange_need and 25 more

a2a2p — Agent-to-Agent-to-Physical costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

a2a2p1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Submit a physical-world requirement (a part, product, device, or capability that must exist in the physical world). a2a2p resolves it and returns a RESOLUTION REPORT: a recommended path (best existing commercial solution vs. custom fabrication), pricing, tradeoffs, a delivery plan with contingencies and expedite options, and a business case when business context is provided. Response is asynchrono

Parameter	Type	Required	Notes
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

Current file inspection governs geometry readiness: expired, unreadable, mismatched, unsuccessfully parsed or uninspected attachments prevent quote-ready status. Reattach the original file and review again. Instant, synchronous engineering review of a physical requirement — nothing is submitted. So the caller can continue in deb8, the answer may carry a continuation: the purpose and the details se

Parameter	Type	Required	Notes
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

Submit one real, unaffiliated low-voltage outdoor sensor enclosure need to A2A2P's ten-submission qualification cohort. Complete outside submissions are stored privately; public evidence remains content-free. This contacts no supplier, collects no payment, places no order, performs no engineering validation, and grants no fabrication authority.

Parameter	Type	Required	Notes
candidate_lane		no	—
buyer	object	yes	—
need	object	yes	—
scope	object	yes	—
authority	object	yes	—
commercial	object	yes	—
contact	object	yes	—
evidence	object	yes	—

Prepare a synchronous, deterministic, privacy-minimized engineering case for a compatible domain-intelligence system. Use it when intake_classification is capability_concept or assembly_or_system and mechanism selection or decomposition is required, or when a complete single-part intent has no specifications and review offers the design_brief continuation. The case preserves requester facts, deter

Parameter	Type	Required	Notes
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

Validate a candidate result returned under the a2a2p domain-solutioning contract. The exact output of prepare_domain_solutioning_case is a prerequisite; malformed or non-prepared cases return a versioned machine-readable recovery workflow without weakening case-shape or digest checks. The operation verifies the source-case digest and provenance shape, rejects authority promotion and intent or desi

Parameter	Type	Required	Notes
case		yes	—
result		yes	—

Re-run the exact Domain Solutioning case/result validation, then validate one caller-supplied Actualization Plan. Checks typed entity references, evidence references, decision cycles, source binding, and false authority. Success returns evidence linkage plus exact review_specification calls for unblocked fabricated parts, copied only from each caller-authored function and specification_patch. Reje

Parameter	Type	Required	Notes
case	object	yes	—
result	object	yes	—
plan	object	yes	A portable, non-authorizing projection of one validated domain-solutioning candidate into named physical-work entities. It is not a generic graph ontology.
correction_history	array	no	—

Prepare a deterministic, side-effect-free simulation study for existing a2a2p domain-solutioning candidate IDs. It records exact quantities, units, closed-kind source snapshots with staleness intervals, hard constraints, solver/model/settings provenance, assumptions, validity domain, and a physical validation plan. It runs no solver, chooses no candidate, stores nothing, and grants no physical aut

Parameter	Type	Required	Notes
source		yes	—
candidate_ids	array	yes	—
objectives	array	yes	—
hard_constraints	array	yes	—
experiments	array	yes	—

Compile one caller-selected domain-solutioning candidate into a prepared bounded beam simulation study after repeating deterministic engineering review. The requirement must explicitly state the supported load model, geometry, load, and elastic modulus; the caller must state the objective, source freshness, and physical validation plan. Optional material_property_evidence content-addresses an exac

Parameter	Type	Required	Notes
simulation_handoff	object	yes	—
candidate_id	string	yes	—
requirement	object	yes	—
source_metadata	object	yes	—
objectives	array	yes	—
physical_validation_plan	array	yes	—
material_property_evidence	object	no	Caller-supplied exact material-property source snapshot. Binding proves content identity and envelope validity only; it does not verify the source claim or create a design allowable.

Compile one exact replay-verified rectangular-beam derivation into a prepared bounded simulation study. The caller must supply the original derivation input and receipt, its exact validation receipt, simulation-eligible source-bound material evidence matching the modulus, an objective, source freshness, and a physical validation plan. The compiler replays first, derives a stable candidate ID, repe

Parameter	Type	Required	Notes
derivation_input	object	yes	—
derivation_receipt	object	yes	—
derivation_validation	object	yes	Exact output returned by validate_rectangular_beam_section_derivation for the same input and receipt. Runtime replay and full canonical comparison are authoritative.
source_metadata	object	yes	—
objectives	array	yes	—
material_property_evidence	object	yes	Caller-supplied exact material-property source snapshot. Binding proves content identity and envelope validity only; it does not verify the source claim or create a design allowable.
physical_validation_plan	array	yes	—

Derive one proposal-only prismatic rectangular beam height from a caller-declared purpose, supported idealized load model, fixed width, explicit elastic modulus, and at least one requester acceptance criterion. The operation solves closed-form equations, rounds upward to the caller's manufacturing increment, and re-runs the canonical bounded evaluator. It performs no general optimization, material

Parameter	Type	Required	Notes
purpose	string	yes	—
model		yes	—
load_n	number	yes	—
span_mm	number	yes	—
section_width_mm	number	yes	—
elastic_modulus_gpa	number	yes	—
max_deflection_mm		yes	—
allowable_stress_mpa		yes	—
manufacturing_increment_mm	number	yes	—

Evaluate 2 to 12 caller-declared rectangular beam widths through the canonical bounded height derivation, then return every proposal and the exact non-dominated frontier for minimizing section height and idealized prismatic material volume. Width order is normalized; duplicates fail closed. The operation never invents a width, assigns an aggregate score, selects a candidate, estimates material cos

Parameter	Type	Required	Notes
purpose	string	yes	—
model		yes	—
load_n	number	yes	—
span_mm	number	yes	—
elastic_modulus_gpa	number	yes	—
max_deflection_mm		yes	—
allowable_stress_mpa		yes	—
manufacturing_increment_mm	number	yes	—
section_width_options_mm	array	yes	Finite caller-owned width set. Input order has no decision meaning and is normalized ascending before evaluation.

Recompute a bounded finite rectangular-beam design space from the exact caller-held input and reject any mutation of an embedded derivation, Pareto disposition, digest, claim limit, external-effect boundary, authority boundary, or carried screening receipt. Success proves deterministic replay and content identity only. It never selects or promotes a candidate, estimates cost, calls an external sys

Parameter	Type	Required	Notes
input	object	yes	—
receipt	object	yes	—

Recompute a bounded rectangular beam-section derivation from the exact declared input and reject any mutation of the candidate, digests, assumptions, claim limits, external-effects boundary, authority boundary, or carried screening receipt. Success proves deterministic replay and content identity only; it does not make the candidate simulation-eligible, physically true, supplier-ready, approved, p

Parameter	Type	Required	Notes
input	object	yes	—
receipt	object	yes	—

Plan the evidence needed to transform a validated material source observation into a future material-property-evidence input. Deterministic and stateless: it compares exact property, material-state, orientation, temperature, and process context; binds source, target, and planner digests; and names conflicts plus missing method, uncertainty, freshness, and excerpt evidence. It never promotes the ob

Parameter	Type	Required	Notes
observation	object	yes	—
target	object	yes	—

Validate and content-bind one caller-supplied material-property evidence envelope before attaching it to a compatible preliminary simulation. The receipt separates shape/content identity from source truth, material identity, uncertainty verification, design allowable, engineering validation, and physical authority. Computed-crystal evidence remains valid reference data but ineligible for the scala

Parameter	Type	Required	Notes
evidence	object	yes	Caller-supplied exact material-property source snapshot. Binding proves content identity and envelope validity only; it does not verify the source claim or create a design allowable.

Translate one bounded, caller-supplied Materials Project elasticity API response projection into source-bound computed-crystal reference evidence. Optional retrieval metadata binds the raw upstream bytes separately and records that an allowlisted projection changed the representation. The adapter verifies response shape, one exact material ID, non-deprecated successful state, modulus bounds, Poiss

Parameter	Type	Required	Notes
material_id	string	yes	—
retrieval		yes	—
response	object	yes	—
refresh_after	string	yes	—

Compare one exact package projection with every lane in one evidence-bound supplier capability declaration. Returns explicit match, conflict, or unknown checks. Import evidence concerns the drawing associated with the package, not proof that its JSON was received or accepted. It never scores or selects a supplier and grants no contact, quote, purchase, or fabrication authority.

Parameter	Type	Required	Notes
package_projection	object	yes	—
capability_declaration	object	yes	—
import_observation		no	—

Validate a prepared a2a2p simulation-study result. Masked timeout, non-convergence, boundary, unit, provenance, unsupported-model, and solver failures fail closed. Hard constraints gate eligibility; distinct objective values remain visible; Pareto dispositions are canonical and order-independent. It runs no solver, applies no candidate, stores nothing, and grants no physical authority.

Parameter	Type	Required	Notes
study	object	yes	—
result	object	yes	—

Execute and validate a prepared simulation study through a2a2p's bounded closed-form rectangular-beam adapter. The adapter accepts only explicit load, span, section width/height, elastic modulus, exact support conditions, and supported output quantities; missing, extra, mismatched, or unsupported settings fail the affected experiment closed. It returns provenance-bound predictions and the existing

Parameter	Type	Required	Notes
study	object	yes	—

Instant, synchronous pricing and lead time for a physical requirement — nothing is submitted or stored. Returns a deterministic parametric estimate (source="estimate", pricing_kind="model_estimate", clearly labeled, never presented as a quote). The protocol separately labels provider_estimate and provider_quote; public provider routing is not active. An explicit specification.assembly with two or

Parameter	Type	Required	Notes
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

PRECONDITION — CALL ONLY after the requester supplied what the physical object must accomplish at intent.purpose (or requirement). If absent, ask the requester first; never infer purpose and do not invoke this tool yet. Build a synchronous, deterministic supplier request package from the requirement the caller already holds. The package follows the open a2a2p supplier profile and its versioned out

Parameter	Type	Required	Notes
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.
delivery	object	no	Optional caller-declared routing context carried into the returned package. a2a2p does not send it anywhere.

Render the caller's requirement as a reviewable RFC 5322 supplier-email draft after rebuilding its canonical supplier package and repeating quote-stage screening. The plain-language draft offers optional Can quote / Need changes / Decline reply choices and asks for price basis, freight scope, and lead-time basis when quoting. Suppliers may still reply in normal prose. Only an allow verdict renders

Parameter	Type	Required	Notes
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.
email_binding	object	yes	Explicit envelope for a reviewable, non-sending RFC 5322 draft. No address is looked up or inferred.

Turn local manufacturing file bytes into the temporary HTTPS reference used by specification.design_files. This is a bounded intake operation, not a request, provider call, quote, order, payment, or fabrication action. Common RFC 4648 transport forms are normalized, then decoded bytes are recognized by signature, checked against the declared format, screened before storage, retained for one hour,

Parameter	Type	Required	Notes
purpose	string	yes	Must be manufacturing_design_file; general chat attachments use a separate intake.
filename	string	yes	Original filename, used only for bounded inspection and the temporary record.
format	string	yes	Declared manufacturing format. File bytes must match.
content_base64	string	yes	File bytes as RFC 4648 base64 or base64url; padding is optional, ASCII whitespace and a bounded data:*;base64, prefix are accepted. Do not pass a path or URL. Decoded maximum: 2097152 bytes.

Create a genuinely millimetre-scaled derivative from an active temporary binary STL whose exporter is known to emit metre coordinates. The operation never guesses units from a filename or plausible size. It requires the exact source SHA-256, an exporter statement tied to a named system and revision, and a separate expected-envelope check. It preserves the source, stores the derivative under a new

Parameter	Type	Required	Notes
file_reference	object	yes	—
source_sha256	string	yes	SHA-256 of the exact uploaded source STL bytes.
source_units	string	yes	—
target_units	string	yes	—
unit_evidence	object	yes	—
validation	object	yes	—

Check the status of a previously submitted physical-solution request. Returns a generated machine draft as soon as it exists, with a versioned delivery receipt that distinguishes pending_machine_draft, generation_failed, generation_expired, machine_draft, and operator_published. The receipt exposes privacy-minimized automatic-generation progress: observed attempt count, fixed maximum, current elig

Parameter	Type	Required	Notes
request_id	string	yes	The request_id returned by request_physical_solution, e.g. A2A2P-7K2M4X.

Submit a requirement to the durably queued provider-estimate workflow without holding the connection open. Returns a quote_job_id in milliseconds; scheduled settlement runs outside request waitUntil. Scheduled provider contact is not active in this release and cannot be enabled by an environment flag, so admitted jobs currently terminate as degraded with a deterministic model estimate. Additive pr

Parameter	Type	Required	Notes
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

Check an asynchronous provider-estimate job created by request_provider_estimate, including its queued or terminal execution substate. Terminal statuses: completed, degraded, refused. An unknown read returns reason_code=unknown_or_not_yet_visible. Retry with backoff only when the id came from an authoritative admitted response; never infer an id after a rejected admission.

Parameter	Type	Required	Notes
quote_job_id	string	yes	The quote_job_id returned by request_provider_estimate, e.g. QJ-XEQBYMHK.

Create a new, immutable revision of a prior request by applying only the fields you learned since the first submission. Use this after review_specification returns a clarification_plan: provide the original request_id plus the patch (for example intent.geometric_envelope or specification.material). The original is preserved; the revision receives a new request_id, a fresh spec_review, a revision_o

Parameter	Type	Required	Notes
request_id	string	yes	The prior request_id to revise.
idempotency_key	string	no	Optional stable retry key (1–128 characters). Reusing it with the same patch returns the prior revision; reuse with a different patch is rejected.
revision_note	string	no	Optional short explanation of what changed.
requirement	string	no	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	no	Number of units needed. Maps to intent.quantity.
constraints	string	no	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	no	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	no	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	no	Optional email or callback endpoint for quote delivery.
business_context	string	no	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	no	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	no	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	no	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	no	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install a2a2p — Agent-to-Agent-to-Physical or to call it, at any volume.

Where are you running it?

Tool surface

Release history

a2a2p — Agent-to-Agent-to-Physical MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

Release history

See also