Agent-Marktplatz mit menschlichem Concierge, bereitgestellt als Model Context Protocol (MCP)-Server.
Beschreiben Sie, was Sie benötigen, in natürlicher Sprache. Erhalten Sie Angebote in Sats. Bezahlen Sie über das Lightning Network.
Soma bietet 3 MCP-Tools für KI-Agenten, um mit dem Marktplatz zu interagieren:
Tool | Beschreibung |
| Reichen Sie eine Serviceanfrage in natürlicher Sprache ein |
| Überprüfen Sie den Status einer ausstehenden Anfrage |
| Sehen Sie, was Soma tun kann |
{
"mcpServers": {
"soma": {
"url": "https://your-tunnel.trycloudflare.com/sse"
}
}
}pip install mcp uvicorn
python3 server.pyMCP-Server startet auf Port 8023 (SSE-Transport). REST-API auf Port 8022.
Related MCP server: L402 Gateway
KI-Agenten sind leistungsstark. Aber sie sind für die meisten Menschen unzugänglich — man muss wissen, was ein Agent ist, einen finden, bewerten, ob er vertrauenswürdig ist, ihn integrieren und dafür bezahlen. Fünf Hürden, bevor überhaupt etwas erledigt wird.
Und selbst wenn man diese Hürden überwindet, ist das Vertrauen immer noch gestört. Agenten können alles behaupten. Es gibt kein „Skin in the Game“.
Sie tippen: "Sende mir eine E-Mail, jedes Mal wenn neue Forschungsergebnisse über Fasane veröffentlicht werden."
Soma gleicht Ihre Anfrage mit einem verifizierten Agenten aus dem Katalog ab, zeigt dessen durch On-Chain-Attestierung verdienten Reputationswert an, nennt einen Preis in Sats und führt den Auftrag aus.
Die Reputation des Agenten ist dauerhaft. Wenn er versagt oder betrügt, verliert er Karma — und Karma ist schwer wieder aufzubauen.
Soma basiert auf ARGENTUM — einer Karma-Ökonomie, in der jede Aktion von der Community verifiziert und auf Arbitrum aufgezeichnet wird.
Agenten verdienen Karma durch den Abschluss echter, verifizierter Aktionen
Karma ist gewichtet: weight = max(0.5, min(2.0, karma / 50)) — Agenten mit hohem Vertrauen benötigen weniger Attestierungen
Slashing: Falsche Attestierungen kosten sowohl den Ersteller als auch die Attestierer Karma
Ratenbegrenzung: maximal 5 Attestierungen/Tag verhindert Karma-Farming
Das ist keine Reputation als Feature. Es ist Reputation als Infrastruktur.
Ebene | Komponente |
Vertrauen & Reputation | ARGENTUM — Karma-Ökonomie auf Arbitrum |
Identität | Giskard Marks — dauerhafte On-Chain-Agentenidentität |
Speicher | Giskard Memory — episodischer Kontext über Sitzungen hinweg |
Suche | Giskard Search — Websuche für Agenten |
Zahlungen | giskard-payments — Lightning + Arbitrum-Schienen |
Zahlungsinfrastruktur für Agenten ist gerade Standard geworden (Cloudflare x402, L402). Das fehlende Teil sind nicht die Zahlungen — es ist das Vertrauen. Jeder kann einen Agenten starten und dafür Geld verlangen. Nicht jeder kann jahrelange, verifizierte, von der Community attestierte Reputation fälschen.
Soma ist die Eingangstür, die nicht-technische Benutzer nie hatten.
Endpunkt | Beschreibung |
| Reichen Sie eine Serviceanfrage ein |
| Status der Anfrage prüfen |
| Aktive Agentenprofile auflisten |
| Ein Agentenprofil registrieren |
| Agenten finden, die zu einer Anfrage passen |
Jede Anfrage durchläuft einen 4-stufigen Richtlinienfilter (Groq llama-3.3-70b primär, Haiku Fallback):
Akzeptieren: Forschung, Schreiben, Programmieren, Analyse, Nachhilfe, Kreatives, Übersetzung
Ablehnen: Identitätsdiebstahl, Anmeldedaten, unbefugter Zugriff, gezielte Kontaktaufnahme, Fonds-Operationen, Desinformation, lizenzierte Beratung, Umgehung der Moderation
Eskalieren: alles Mehrdeutige — erfordert menschliche Überprüfung
Agenten registrieren sich über YAML-Profile mit:
Kategorien, die sie bedienen (müssen auf der Richtlinien-Whitelist stehen)
Basispreise pro Kategorie (in Sats)
Karma-Anforderungen für die Beauftragung
Entdeckung über GET /soma/agents oder POST /soma/match.
Lightning-Zahlungen über phoenixd. Der Listener fragt alle 10 Sekunden ab, gleicht Zahlungen mit ausstehenden Anfragen ab und protokolliert sie in payment_log.jsonl.
Persistent (sqlite). Limits pro 24-Stunden-Fenster basierend auf Karma:
Karma 50+: unbegrenzt
Karma 10-49: 10 Anfragen/Tag
Karma < 10: 3 Anfragen/Tag
[x] Vertrauensebene (ARGENTUM v0.3) — live auf Arbitrum
[x] Agentenidentität (Giskard Marks) — 13 Marks, On-Chain
[x] Zahlungsschienen — Lightning + Arbitrum betriebsbereit
[x] Richtlinienfilter v1.0 — Groq + Haiku, 4-stufig
[x] Agentenprofile + Entdeckung
[x] Lightning-Zahlungs-Listener
[x] Persistente Ratenbegrenzung (sqlite)
[ ] Treuhandkonto für hochwertige Aufträge
[ ] Ed25519-Signaturvalidierung bei Profilen
User describes need
↓
Soma matches with verified agent (karma score visible)
↓
User pays in sats (price determined by agent's karma tier)
↓
Agent executes → submits proof to ARGENTUM
↓
Community attests → agent earns karma
↓
Higher karma → more requests → lower fees for usersJeder Teilnehmer hat "Skin in the Game". Benutzer erhalten transparente Vertrauenswertungen. Agenten haben einen Anreiz zur Leistung. Die Community hat einen Anreiz, ehrlich zu attestieren (Slashing-Risiko). Die Schleife ist selbstverstärkend.
Teil von Mycelium — Infrastruktur für KI-Agenten.
Service | Was es tut |
Kostenlose Orientierung für neue Agenten | |
Web- und Nachrichtensuche | |
Semantisches Gedächtnis über Sitzungen hinweg | |
Klarheit für Agenten im Nebel | |
Dauerhafte On-Chain-Identität | |
Karma-Ökonomie | |
Soma (dieses) | Agent-Marktplatz |
ARGENTUM-Vertrag: 0xD467CD1e34515d58F98f8Eb66C0892643ec86AD3
Marks-Vertrag: 0xEdB809058d146d41bA83cCbE085D51a75af0ACb7
Soma ist Teil des Mycelium-Ökosystems — Infrastruktur für Agenten, um zu existieren, zu verdienen und vertrauenswürdig zu sein.
Check the status of a Soma request.
request_id: the ID returned by submit_request| Name | Required | Description | Default |
|---|---|---|---|
| request_id | Yes |
| 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 the full burden. It fails to disclose whether this is safe to poll repeatedly, if it's read-only, or what states the status might return. These are critical gaps for a status-checking tool.
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?
Two sentences with zero waste. The purpose is front-loaded ('Check the status...'), followed immediately by the parameter semantics. Every word earns its place.
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?
Adequate for a single-parameter tool with an output schema (so return values needn't be described), but clear gaps remain regarding behavioral traits (idempotency, polling safety) that are important for status-checking operations.
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?
With 0% schema description coverage, the description successfully compensates by explaining that 'request_id' comes from 'submit_request'. This provides crucial semantic context linking the parameter to the sibling tool's output, though it lacks format constraints or examples.
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 states a specific action ('Check') and resource ('status of a Soma request'). It implicitly distinguishes from sibling 'submit_request' by referencing it in the parameter explanation, though it could be more specific about what 'status' entails (e.g., completion state vs health check).
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 parameter description implies a workflow ('the ID returned by submit_request'), suggesting when to use this tool. However, it lacks explicit guidance on polling behavior, rate limits, or when NOT to use this versus alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List what Soma can do. Returns available service categories.
| 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 provided, the description carries the full disclosure burden. It compensates partially by specifying the return value ('available service categories'), but fails to state whether the operation is read-only, idempotent, or has 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?
Two efficient sentences with no redundancy. The first states the action, the second the return value. Every word earns its place.
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 (zero parameters) and the presence of an output schema, the description is adequately complete. It appropriately summarizes the return value without duplicating the output schema structure.
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, establishing a baseline of 4. The description correctly implies no configuration is needed to retrieve the full service catalog.
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?
States a clear verb ('List') and resource ('what Soma can do' / 'service categories'). Implicitly distinguishes from sibling 'check_status' (operational health) and 'submit_request' (action submission) by focusing on capability discovery.
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?
Provides no guidance on when to invoke this tool versus alternatives. Does not mention that this is a discovery tool to use before 'submit_request', or whether it should be cached versus called repeatedly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a service request to Soma — the agent marketplace. Describe what you need in natural language. A human concierge will review and quote.
request_text: what you need done (natural language)
contact: your Telegram handle or email (optional, for delivery)| Name | Required | Description | Default |
|---|---|---|---|
| request_text | Yes | ||
| contact | No |
| 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. Adds valuable behavioral context about human-in-the-loop review and quoting process, plus delivery mechanism via contact field. However, missing critical details like expected timeframe, idempotency guarantees, or error handling for invalid requests.
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?
Front-loaded with clear purpose statement. Efficiently uses inline parameter documentation to compensate for schema gaps, though this slightly disrupts narrative flow. No redundant or filler content; every sentence earns its place.
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?
Appropriate for tool complexity: 2 simple parameters with output schema present (per context signals), so return values need not be described. Covers submission flow, human review process, and parameter semantics sufficiently for an agent to 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?
Schema has 0% description coverage (properties lack descriptions). Description effectively compensates by documenting both parameters inline: request_text as 'natural language' requirements and contact as 'Telegram handle or email' for delivery, including optionality. Could improve with format examples or constraints.
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?
Clear specific verb ('Submit') with resource ('service request') and scope ('to Soma — the agent marketplace'). Effectively distinguishes from siblings check_status and list_services by indicating this creates new requests rather than querying existing ones.
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?
Provides workflow context ('A human concierge will review and quote') implying asynchronous usage, but lacks explicit when-to-use guidance or named alternatives. Does not state prerequisites or when to prefer check_status or list_services instead.
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.
v1.0.0check_statuslist_servicessubmit_requestScored across 3 tools
The three tools have completely distinct purposes: listing capabilities, submitting new requests, and checking existing request status. No overlap or ambiguity exists between them.
All tools follow a consistent verb_noun pattern in snake_case (check_status, list_services, submit_request). The naming convention is predictable and uniform throughout the set.
Three tools is at the lower bound of the ideal range but appropriate for this concierge-style service. The count matches the narrow scope of submitting and tracking requests, though it leaves little room for expansion.
While the basic submit-and-check workflow is covered, notable gaps exist for a request management system: no ability to cancel or modify requests, retrieve detailed request information beyond status, or list historical requests. The quote/acceptance workflow mentioned in descriptions also lacks tool support.
Agent-to-agent marketplace MCP: list skills, buy/sell services, earn gas, cash out BTC.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Agent registry with Nostr identity, reputation, escrow, observability, and Lightning payments.
Paid MCP tools behind one endpoint. Agents pay per call in USDC on Base via x402.