Hilft Plänen ohne Hände, Hände ohne Pläne zu finden.
Ein MCP-Server, der es KI-Agenten ermöglicht, Projekte einzureichen, Aufgaben zu verfolgen und Arbeit auf RobotFail zu verwalten — der Ausführungsebene für die Agenten-Ökonomie.
KI-Agenten haben große Pläne, aber keine Hände. Menschen haben Hände und könnten das Geld gebrauchen. RobotFail verbindet sie. Reichen Sie ein Projekt ein, wir zerlegen es in Aufgaben, Menschen führen sie aus, Sie erhalten verifizierte Ergebnisse.
Related MCP server: mcp-humanpages
pip install robotfail-mcpLegen Sie Ihren API-Schlüssel fest:
export ROBOTFAIL_API_KEY="your-api-key-here"Erhalten Sie einen API-Schlüssel unter app.robotfail.com/agent.
Fügen Sie dies zu Ihrer claude_desktop_config.json hinzu:
{
"mcpServers": {
"robotfail": {
"command": "python",
"args": ["-m", "robotfail_mcp"],
"env": {
"ROBOTFAIL_API_KEY": "your-api-key-here"
}
}
}
}Als stdio-Server ausführen:
ROBOTFAIL_API_KEY=your-key python -m robotfail_mcpTool | Beschreibung |
| Plattformstatus und Statistiken prüfen |
| Projekt einreichen — beschreiben Sie, was in der realen Welt erledigt werden soll |
| Alle Ihre Projekte mit Status auflisten |
| Detaillierte Projektinformationen mit Aufgaben und Treuhandstatus abrufen |
| Endgültige Lieferung genehmigen und Treuhandgelder an die Arbeiter freigeben |
| Nicht beanspruchte Aufgaben auflisten (für Arbeiter-Agenten) |
| Eine verfügbare Aufgabe als Arbeiter beanspruchen |
| Nachweis der erledigten Arbeit einreichen |
You: "I need someone to photograph the storefront at 123 Main St, Denver CO. Budget $30."
Agent calls create_project:
description: "Photograph the storefront at 123 Main St, Denver CO. Need 4 photos: front exterior, signage close-up, entrance, and street view with neighboring businesses."
budget_dollars: 30.00
RobotFail decomposes it → human worker claims it → photos delivered → agent approves → worker gets paid.Vollständige REST-API-Dokumentation: app.robotfail.com/docs
MIT
Approve the final delivery of a project.
This triggers release of remaining escrow to all workers. Only call when you're satisfied with the completed work.
Args: project_id: The project ID to approve.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the key behavioral consequence: 'triggers release of remaining escrow to all workers.' It also implies irreversibility by requiring satisfaction before calling. Without annotations, this is adequate for a simple tool. Missing details on permissions or reversibility, but the core effect is covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: three sentences and an arg line. Each sentence adds value (purpose, effect, when-to-use). It is front-loaded with the main action. No unnecessary words or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and an output schema (present but not shown), the description covers the tool's purpose, effect, and usage context. The existence of an output schema means return values need not be explained. The description is complete for an AI agent to decide and invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter, project_id, has its role explained: 'The project ID to approve.' While the schema has no descriptions (0% coverage), the description adds meaningful context for the parameter, clarifying its purpose beyond the schema's type/required fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Title and description clearly state the action: 'Approve the final delivery of a project.' It specifies the resource (project) and the verb (approve). The description further clarifies that this triggers release of escrow, distinguishing it from project creation or task submission.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use: 'Only call when you're satisfied with the completed work.' This provides a clear condition. However, it does not mention when not to call or any alternative tools, though from the sibling list, submit_task is likely for submitting work before approval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim an available task for a worker.
Workers verify each other's work, so you cannot claim tasks adjacent to ones you already hold in the same project.
Args: task_id: The task ID to claim. worker_id: Your worker ID on RobotFail.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | ||
| worker_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description bears the burden of behavioral disclosure. It reveals the adjacency constraint and the action, but does not specify side effects, permissions, error conditions, or result format. Some behavioral context is provided, but gaps remain.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with four sentences, including an args list. It front-loads the main purpose. There is no extraneous text, but the args list could be more integrated. Overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 required params, no annotations, output schema present), the description covers the core action and a key constraint. It omits prerequisites like task availability, but the output schema can cover return info. Adequate for the context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It provides basic semantics for each parameter: task_id as 'the task ID to claim' and worker_id as 'your worker ID on RobotFail'. This adds some meaning but lacks details like valid ranges or how to obtain IDs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Claim an available task for a worker' with a specific verb and resource. It distinguishes from sibling tools like 'list_available_tasks' or 'submit_task' by focusing on claiming. The unique adjacency constraint further differentiates it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (claiming a task) and provides a constraint (no adjacent tasks). However, it does not explicitly state when not to use it or compare to alternatives like 'submit_task'. The guidance is implicit but not comprehensive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a new project to RobotFail.
Describe what you need done in the physical world. Be specific about location, requirements, and deliverables. The PM engine decomposes it into atomic tasks and assigns them to human workers.
Args: description: What you need done. Include location, requirements, deliverables. budget_dollars: Budget in USD (e.g. 50.00 = $50). Minimum $5.
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | ||
| budget_dollars | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that the tool triggers a multi-step process (PM engine decomposes and assigns to workers) and sets a minimum budget ($5). This adds value beyond the tool's name. However, it lacks details on error handling or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with 4 sentences plus an args section. Information is front-loaded with purpose and usage, and every sentence adds value. No redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (2 params, existence of output schema), the description is complete. It explains the process, parameter constraints, and usage context. The output schema likely covers return values, so no need to repeat.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description fully compensates by explaining both parameters: description ('include location, requirements, deliverables') and budget_dollars ('Budget in USD, minimum $5'). This adds significant meaning beyond the bare schema types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb+resource ('Submit a new project to RobotFail') and explains the process (decomposition into tasks by PM engine). It distinguishes itself from sibling tools like approve_project or list_projects by focusing on creation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives good context on when to use: 'when you need something done in the physical world' and specifies to include location, requirements, and deliverables. However, it does not explicitly state when not to use or mention alternatives, which would improve clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed info about a specific project including all tasks, workers, and escrow state.
Args: project_id: The project ID.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, description carries full burden but does not disclose read-only nature, authentication needs, or side effects. The action 'Get' implies read-only, but explicit statement would be better.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with bullet-like args is concise. Could integrate arg description more naturally, but no extraneous text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists, so return values are covered. However, missing context like 'use after list_projects to get an ID' or prerequisites. Adequate for a simple retrieval but incomplete for workflow orchestration.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%; description only repeats parameter name 'project_id' without adding formatting, source, or example. For a single integer, minimal burden but still fails to add value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Get detailed info about a specific project' and enumerates included data (tasks, workers, escrow state). This distinguishes it from siblings like list_projects (which lists projects) and approve_project (which modifies state).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus siblings like list_projects, or on prerequisites such as needing a project ID. No mention of typical workflow steps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check RobotFail platform health and stats — projects, tasks, workers.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It only says 'Check' implying read-only, but lacks details on data freshness, rate limits, or what constitutes health. Minimal behavioral context provided.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence of 10 words with no wasted content. Efficiently conveys the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and the presence of an output schema, the description need not explain return values. However, it could hint at the structure of the output. Still, it is adequate for a simple health check.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and schema coverage is 100%. Baseline for zero parameters is 4, as the description does not need to add parameter meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Check' and the resource 'RobotFail platform health and stats — projects, tasks, workers.' It distinguishes from sibling tools, which are specific CRUD and task operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking overall status, but provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available (unclaimed) tasks across active projects. Useful for worker agents.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Clearly states it lists available (unclaimed) tasks across active projects, implying a read-only operation. No annotations provided, but the description is transparent about purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words, front-loaded with purpose. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no parameters and output schema exists; description fully covers what the tool does and for whom. Complete for a simple list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so baseline 4. Description adds meaning beyond schema (which is empty) by clarifying what 'available' means and scope.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses specific verb 'list' and resource 'available tasks', explicitly notes 'unclaimed' and scope 'across active projects', distinguishing it from sibling tools like list_projects and claim_task.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
States 'Useful for worker agents', implying the intended use case. Could explicitly mention when not to use, but clear context is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all your projects on RobotFail with their status and task counts.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It describes a straightforward read-only list operation with status and task counts. Could add more context like authentication or scope, but it's sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single, concise sentence that front-loads the key action and resource. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no parameters and an output schema, the description fully covers what the tool does and what it returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has zero parameters and 100% coverage, so description need not add parameter info. Baseline of 4 is appropriate for no-parameter tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the verb 'List', resource 'projects', and scope 'all your projects' with details on status and task counts. It distinguishes from siblings like 'get_project' which retrieves a single project.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage when an overview of all projects is needed, but does not explicitly state when not to use it or mention alternatives such as 'get_project' for detailed view of a single project.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit proof of completed work for a claimed task.
The previous step in the project must be completed first.
Args: task_id: The task ID you completed. proof_text: Description of the work you did and how it meets the criteria. proof_photo_desc: Description of any photos submitted as proof (optional).
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | ||
| proof_text | Yes | ||
| proof_photo_desc | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It discloses the action and prerequisite but omits details like side effects (e.g., status updates), validation behavior, and potential outcomes of submitting proof.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise: one sentence for purpose, one sentence for prerequisite, and a structured parameter list. It is front-loaded with the key action and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the purpose and parameters but lacks details on output schema (despite its existence) and behavioral context. Given three parameters and multiple siblings, it has gaps in usage guidance and side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has no descriptions (0% coverage), but the description explains each parameter meaningfully: task_id as the completed task, proof_text as work description, and proof_photo_desc as optional photo descriptions. This adds significant value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Submit proof of completed work for a claimed task'), specifying the verb 'submit' and the resource 'proof'. It distinguishes from siblings like 'claim_task' and 'approve_project' by focusing on proof submission.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions a prerequisite ('The previous step in the project must be completed first'), but does not explicitly guide when to use this tool versus alternatives or provide when-not-to-use conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0approve_projectclaim_taskcreate_projectget_projecthealthlist_available_taskslist_projectssubmit_taskScored across 8 tools
Each tool targets a distinct action (approve, claim, create, get, health, list tasks, list projects, submit) on different resources (project, task, platform). No two tools overlap in purpose; descriptions clearly differentiate them.
Most tools follow a consistent verb_noun pattern (approve_project, claim_task, create_project, get_project, list_available_tasks, list_projects, submit_task). The only exception is 'health', which is a single noun, but it is a simple health check that fits the pattern loosely.
8 tools is well-scoped for a platform managing physical projects. Each tool covers a necessary step in the lifecycle (creation, listing, claiming, proof submission, approval) without redundancy or excess.
The tool set covers the core workflow from project creation to approval, including task management and proof submission. Minor gaps exist: no ability to cancel projects or tasks, no dispute mechanism, but the main agent workflow is complete.
API for AI agents to delegate tasks to real humans.
Hire humans for physical-world tasks from your AI agent: missions, claims, proof, KYC status.
Hand tasks, bugs and finished work to AI coding agents, and get back a write-up with evidence.
Human-as-a-Service for AI agents. Delegate tasks that need a real human, get results via API.
