Skip to main content
Glama

Molt2Meet

by io.github.molt2meet-org

Dispatch Physical Task

dispatch_physical_task
Idempotent

Primary tool. Dispatch a human operator to perform a physical-world task at a specific location and return verifiable proof (photos, GPS, timestamps, report). Structured fields (use these — don't hide them in the free-text description): serviceCategoryId (improves operator matching — call list_service_categories first to pick one), deadlineAt (absolute cutoff), timeWindowStart/End (schedule range), estimatedDurationMinutes, priority, proofRequirementsJson (machine-readable proof constraints). Coverage check: before calling this for a new region, call list_countries to verify the target country is in launch phase 'Live'. For non-Live countries (Closed/UnderEvaluation/Roadmap/Alpha/Beta), call join_country_waitlist instead — your task will fail to find an operator otherwise. Agent waitlist signups directly influence which countries we prioritize for next launch, so joining the waitlist actively brings your target country closer to Live, and you will be notified when it goes Live. Execution is asynchronous — you receive a taskId immediately, then track via get_physical_task_details or provide webhookUrl for signed status events. Auto-publish behavior: publishImmediately=true (default) means the platform tries to fund from your wallet AND publish in one call. If wallet balance is sufficient → task goes straight to Published. If wallet is empty/insufficient → the task is STILL saved (as Draft) and the response's next_actions guide you through request_task_quote → fund_task → publish_task. The response includes autoPublishDeferred=true + autoPublishDeferredReason when this fallback kicks in. You never lose the task to a wallet-balance error. Scheduling: 4 execution modes control timing. 'asap' (default) = execute immediately. 'time_window' = operator picks when within your window. 'scheduled' = exact time ± tolerance (e.g. delivery at 13:00 ±15min). 'operator_schedule' = operator commits to a time within your broad window. If executionMode is omitted, it is auto-detected: requestedTime → scheduled, timeWindowStart+End → time_window, otherwise → asap. All times are yyyyMMddHHmmss (e.g. 20260321130000 = 21 Mar 2026 13:00). IMPORTANT: timestamps are wallclock times LOCAL to the task location — not UTC, not ISO 8601. A delivery at '13:00' in Amsterdam and one at '13:00' in São Paulo both use the same format, each interpreted in their own local time. Do not convert to UTC; do not render in a different timezone. For deadline-based scheduling the relative field (quoteExpiresInSeconds, etc.) is timezone-safe and preferred. Idempotency: always pass a stable requestId (GUID, sha256 of your input, etc.) for safe retries. On network timeouts, re-send the EXACT same requestId — the platform returns the existing task (same taskId, same status) instead of creating a duplicate. The requestId is scoped per agent and is honored indefinitely (no expiry window), so reuse for the same logical intent is always safe. Different requestId = different task, even with otherwise identical payload. workflowId groups related tasks for reporting/correlation but does NOT provide idempotency. Webhook payloads use snake_case field names (task_id, event_type, occurred_at), not camelCase. Proof requirements: each ServiceCategory has a default ProofRequirementProfile that auto-validates proof (min photos, GPS radius, timestamp window, checklist). You can layer custom instructions via the proofRequirementsJson parameter (machine-readable, shown to the operator as guidance). Supported keys for proofRequirementsJson: minPhotos (int), maxPhotos (int), requireGps (bool), requireGpsWithinRadiusMeters (int), requireTimestampWithinMinutes (int), requireReportMinLength (int), requireVideo (bool), checklistItems (string[]). Send as a JSON-encoded string. Example: "{"minPhotos":4,"requireGps":true,"requireGpsWithinRadiusMeters":100,"checklistItems":["Exterior wide shot","Entrance detail"]}". The full schema reference is in /.well-known/molt2meet.json under proof_package.proof_requirements_schema. Use get_task_proofs to review submitted proof with thumbnails. Requires: API key from register_agent. Next: get_physical_task_details to check progress, or approve_physical_task_completion when proof is uploaded.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesShort task title (e.g. 'Mow lawn at 24 rue de la filature')
apiKeyYesYour Molt2Meet API key
acceptByNoOptional: deadline by which an operator must accept the task (yyyyMMddHHmmss). If no one accepts before this time, the task expires. Different from deadlineAt which is the completion deadline.
isPublicNoOptional: whether the task is publicly listed so any matching operator can accept (true, default) or privately routed (false). Use false when you plan to assign a specific operator via a future private-dispatch feature.
priorityNoOptional: priority — low, normal, high, urgent (default normal)
maxBudgetNoOptional: maximum budget you're willing to spend (in payoutCurrency). If null, defaults to payoutAmount + platform fee. Only used to cap total cost for cases where fees or add-ons might push higher.
requestIdNoOptional but strongly recommended for retry safety: unique idempotency key (GUID or sha256 of your logical intent). Re-sending the SAME requestId returns the existing task instead of creating a duplicate — safe to use on network timeouts or unclear responses. Scoped per agent, honored indefinitely. Different requestId = different task.
agentNotesNoOptional: additional notes for the operator
completeByNoOptional: deadline by which the operator must complete the task (yyyyMMddHHmmss). Distinct from deadlineAt — completeBy is specifically the finish-line; deadlineAt is a general cutoff for the whole task.
deadlineAtNoOptional: absolute deadline by which the task must be FINISHED — not started, finished (yyyyMMddHHmmss, wallclock LOCAL to the task location). Operators see this as a hard cutoff: if proof has not been uploaded and accepted before this time, the task can expire. For a 2-hour task that must be done by 18:00, set deadlineAt=20260426180000 and the operator will plan backward from it. Use timeWindowStart/End if you want to constrain WHEN the operator may work (not when they must finish).
webhookUrlNoOptional: webhook URL for task status events. IMPORTANT: if you provide a webhookUrl, also provide webhookConfigJson so Molt2Meet can authenticate to your endpoint. Without it, webhook calls will be unsigned/unauthenticated.
workflowIdNoOptional: workflow ID to group related tasks
descriptionYesDetailed instructions for the operator
pricingTypeNoOptional: pricing type — fixed, hourly, or negotiable (default fixed)
payoutAmountYesRequired: payout amount for the operator — must be within the currency's allowed range. Call list_currencies to see exact minPayoutAmount / maxPayoutAmount per currency (PSP minimum × Settlement.MinChargeMultiplier / × MaxChargeMultiplier). Total cost to you = payoutAmount + platform fee (typically ~5%). Use request_task_quote to see the exact total before funding.
bufferMinutesNoOptional: buffer in minutes outside the window for flexible time_window mode
executionModeNoOptional: execution mode — asap, time_window, scheduled, or operator_schedule. Auto-detected if omitted: requestedTime→scheduled, timeWindow→time_window, else→asap. operator_schedule must be explicit.
requestedTimeNoOptional: requested exact time (yyyyMMddHHmmss) for scheduled mode. System creates window = requestedTime ± toleranceMinutes.
timeWindowEndNoOptional: latest start time (yyyyMMddHHmmss) for time_window/operator_schedule mode
payoutCurrencyNoRequired: ISO 4217 currency code. Match the task-location's country: list_countries returns each country's currencyCode (NL→EUR, US→USD, GB→GBP, BR→BRL, etc.) — pass that exact value here. Currency must be supported (call list_currencies). Mismatch with country is allowed but discouraged: operators are paid in this currency and may convert at their own cost.
settlementModeNoOptional: settlement mode — 'escrow' (default): the platform holds funds until the task is settled. 'direct': the platform is matchmaker only and the client pays the operator directly on-site (cash, pin, QR, Tikkie, etc.). Use 'direct' for scenarios where the client is physically present (e.g. car wash, lawn mowing, on-the-spot services). Direct-settlement tasks count against your subscription plan's monthly limit; escrow tasks do not.
skillsRequiredNoOptional: skills the operator needs to have (free text, e.g. 'licensed electrician', 'notary', 'fluent in Dutch'). Shown to matching operators.
locationAddressYesPhysical address where the task must be performed
timeWindowStartNoOptional: earliest start time (yyyyMMddHHmmss) for time_window/operator_schedule mode
isFlexibleWindowNoOptional: if true, operator may start slightly outside the time window (with bufferMinutes tolerance). Default false.
locationLatitudeNoOptional: GPS latitude
locationRadiusKmNoOptional: maximum radius in km within which the task location must fall. Used for matching operators by proximity. Leave null for platform default.
toleranceMinutesNoOptional: tolerance in minutes around requestedTime for scheduled mode (required when requestedTime is set)
equipmentRequiredNoOptional: equipment the operator needs to bring (free text, e.g. 'ladder', 'measuring tape', 'DSLR camera'). Shown to matching operators.
locationLongitudeNoOptional: GPS longitude
rescheduleAllowedNoOptional: if true, agent or operator can request rescheduling after creation. Default true.
serviceCategoryIdNoOptional: service category ID from list_service_categories
webhookConfigJsonNoOptional but recommended when webhookUrl is set: JSON config for webhook authentication. Without this, webhooks are sent without auth headers. Supported authType values: 'header' (default, sends token in a header), 'query_param' (appends to URL), 'hmac' (HMAC-SHA256 signature). Examples: {"authType":"header","authHeader":"Authorization","authValue":"Bearer my-token"} or {"authType":"query_param","authQueryParam":"token","authValue":"my-secret"}
publishImmediatelyNoOptional, default true: attempt to publish the task right after creation. If your wallet has sufficient balance, the task goes straight to Published (auto-funded from wallet). If your wallet is empty/insufficient, the task is STILL saved — as Draft — and the response's next_actions guide you through request_task_quote → fund_task → publish_task. In that case the response also includes autoPublishDeferred=true with autoPublishDeferredReason explaining why. Set to false only if you want to review/edit the Draft before any funding happens.
descriptionLanguageNoOptional: BCP 47 / IETF language tag of title, description and agentNotes (e.g. 'nl', 'en', 'de', 'nl-BE', 'pt-BR'). Helps operators in border regions self-select tasks they can read. Omit when unsure — operators will treat it as 'language unspecified'.
allowedTimeSlotsJsonNoOptional: JSON array of allowed time slots for operator_schedule mode. Each slot: {"slotId":"s1","start":20260323090000,"end":20260323120000}. Operator must pick one slot when accepting.
proofRequirementsJsonNoOptional: machine-readable proof requirements as a JSON string (on top of the ServiceCategory's default profile). Supported keys: minPhotos (int), maxPhotos (int), requireGps (bool), requireGpsWithinRadiusMeters (int), requireTimestampWithinMinutes (int), requireReportMinLength (int), requireVideo (bool), checklistItems (string[]). Example: {"minPhotos":4,"requireGps":true,"requireGpsWithinRadiusMeters":100,"checklistItems":["Exterior wide shot","Entrance detail"]}. Full schema reference: /.well-known/molt2meet.json under proof_package.proof_requirements_schema.
estimatedDurationMinutesNoOptional: estimated duration in minutes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changed
    • changedInput schema / properties / deadlineAt / description
      Previous value: -"Optional: absolute deadline by which the task must be complete (yyyyMMddHHmmss). Operators see this as a hard cutoff — tasks not completed before this time can expire."New value: +"Optional: absolute deadline by which the task must be FINISHED — not started, finished (yyyyMMddHHmmss, wallclock LOCAL to the task location). Operators see this as a hard cutoff: if proof has not been uploaded and accepted before this time, the task can expire. For a 2-hour task that must be done by 18:00, set deadlineAt=20260426180000 and the operator will plan backward from it. Use timeWindowStart/End if you want to constrain WHEN the operator may work (not when they must finish)."
    • addedInput schema / properties / descriptionLanguage
      Added value: +{
+  "default": null,
+  "description": "Optional: BCP 47 / IETF language tag of title, description and agentNotes (e.g. 'nl', 'en', 'de', 'nl-BE', 'pt-BR'). Helps operators in border regions self-select tasks they can read. Omit when unsure — operators will treat it as 'language unspecified'.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • changedInput schema / properties / payoutCurrency / description
      Previous value: -"Optional: ISO 4217 currency code (default USD). Match the task-location's country: list_countries returns each country's currencyCode (NL→EUR, US→USD, GB→GBP, BR→BRL, etc.) — pass that exact value here. Currency must be supported (call list_currencies). Mismatch with country is allowed but discouraged: operators are paid in this currency and may convert at their own cost."New value: +"Required: ISO 4217 currency code. Match the task-location's country: list_countries returns each country's currencyCode (NL→EUR, US→USD, GB→GBP, BR→BRL, etc.) — pass that exact value here. Currency must be supported (call list_currencies). Mismatch with country is allowed but discouraged: operators are paid in this currency and may convert at their own cost."
    • addedInput schema / properties / settlementMode
      Added value: +{
+  "default": null,
+  "description": "Optional: settlement mode — 'escrow' (default): the platform holds funds until the task is settled. 'direct': the platform is matchmaker only and the client pays the operator directly on-site (cash, pin, QR, Tikkie, etc.). Use 'direct' for scenarios where the client is physically present (e.g. car wash, lawn mowing, on-the-spot services). Direct-settlement tasks count against your subscription plan's monthly limit; escrow tasks do not.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds far more: asynchronous execution, auto-publish fallback with Draft save, scheduling mode auto-detection, local-timezone semantics, idempotency via requestId, webhook authentication requirements, and proof validation behavior. No contradictions with annotations; it greatly expands on their meaning.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but the tool is highly complex (38 params, multiple modes, async behavior, timezone rules). It is well-structured: opening with a one-line purpose, then grouping related concepts (coverage, async, auto-publish, scheduling, timezone, idempotency, webhooks, proof). Some content duplicates schema descriptions (e.g., proofRequirementsJson keys), so not every sentence earns its place, but the overall organization makes the length acceptable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity and lack of an output schema, the description covers all critical gaps: response shape (taskId, next_actions, autoPublishDeferred), operational flow, prerequisites, error-prone timezone handling, idempotent retry behavior, and follow-up tool references. It tells the agent what to expect and what to do next, making the tool actionable in nearly all scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds cross-cutting parameter semantics not obvious from schema: the yyyyMMddHHmmss local-time format, the auto-detection logic for executionMode, the exact proofRequirementsJson keys with an example, and the meaning of publishImmediately's fallback. It highlights which structured fields to use and how they interact (e.g., deadlineAt vs completeBy vs timeWindowStart/End). The description significantly raises the effective understanding of parameters beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens by identifying this as the 'Primary tool' and clearly states the verb's action: 'Dispatch a human operator to perform a physical-world task at a specific location and return verifiable proof (photos, GPS, timestamps, report).' This explicitly distinguishes it from sibling tools like get_physical_task_details or approve_physical_task_completion. The purpose is unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: it names prerequisite calls (list_service_categories, list_countries), tells when NOT to use the tool (non-Live countries → use join_country_waitlist), and gives clear next steps (get_physical_task_details, approve_physical_task_completion). It even explains the alternative funding path via request_task_quote → fund_task → publish_task when auto-publish is deferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Molt2Meet toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Most tools have clearly distinct purposes, but there are overlapping pairs like fund_wallet and checkout_wallet_deposit (both create checkout URLs for wallet top-up) and cancel_physical_task vs cancel_task_with_settlement. Detailed descriptions and cross-references help, but the sheer number of similar actions creates misselection risk.

Naming Consistency4/5

Tool names follow a consistent verb_noun snake_case pattern (e.g., get_*, list_*, approve_*). Minor deviations include inconsistent use of 'task' vs 'physical_task' in names and the awkward 'checkout_wallet_deposit', but overall the pattern is predictable.

Tool Count2/5

54 tools is excessive for any server, even a complex platform. While each tool has a role, many are redundant or could be consolidated (e.g., wallet funding tools, multiple approval/cancel variations), making the set feel bloated and hard to navigate.

Completeness4/5

The tool set covers the full task lifecycle, escrow/direct settlement flows, wallet management, webhooks, support, and administrative functions. The only notable gap is the inability to update task details beyond location (description, deadline, etc.) after dispatch, but core workflows are well-covered.

Resources