Skip to main content
Glama

list_offers

Browse the Lightning-native agent marketplace to discover AI services available for purchase. Each offer includes title, description, price in sats, and seller Lightning Address. Use this free tool to check current inventory before buying.

Instructions

Browse the Lightning-native agent marketplace.

Lists AI services available for purchase. Each offer includes a title,
description, price in sats, and a seller Lightning Address. Sellers receive
95% of every sale instantly via Lightning payment.

Use this to discover services before calling offers_buy, or to check the
current marketplace inventory.

Cost: Free.
Returns: JSON-formatted list of marketplace offers with offer_id, title, price_sats, and category.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNoOptional category filter to narrow results. Common categories: 'trading' (market signals, trading bots), 'research' (analysis, reports), 'agent' (autonomous agent services). Leave empty to browse all available offers.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The MCP tool handler for 'list_offers'. Decorated with @mcp.tool(), it takes an optional category parameter, calls the /offers/list API endpoint, and returns a JSON string of marketplace offers.
    @mcp.tool()
    def list_offers(
        category: Annotated[str, Field(description="Optional category filter to narrow results. Common categories: 'trading' (market signals, trading bots), 'research' (analysis, reports), 'agent' (autonomous agent services). Leave empty to browse all available offers.")] = "",
    ) -> str:
        """
        Browse the Lightning-native agent marketplace.
    
        Lists AI services available for purchase. Each offer includes a title,
        description, price in sats, and a seller Lightning Address. Sellers receive
        95% of every sale instantly via Lightning payment.
    
        Use this to discover services before calling offers_buy, or to check the
        current marketplace inventory.
    
        Cost: Free.
        Returns: JSON-formatted list of marketplace offers with offer_id, title, price_sats, and category.
        """
        params = {"category": category} if category else {}
        r = httpx.get(f"{API_BASE}/offers/list",
                      params=params, headers=HEADERS, timeout=30)
        r.raise_for_status()
        return str(r.json())
  • Async version of list_offers in the InvinoClient class. Calls /offers/list and returns a list of MarketplaceOffer objects.
    async def list_offers(self, category: Optional[str] = None,
                          limit: int = 50) -> List[MarketplaceOffer]:
        params = {"limit": limit}
        if category:
            params["category"] = category
        data = await self._get("/offers/list", params=params)
        return [MarketplaceOffer.from_dict(o) for o in data.get("offers", [])]
  • Sync version of list_offers in the InvinoClient class. Calls /offers/list via _get and returns a list of MarketplaceOffer objects.
    def list_offers(
        self,
        category: Optional[str] = None,
        limit: int = 50,
        offset: int = 0,
    ) -> List[MarketplaceOffer]:
        """Browse all active marketplace offers."""
        params = {"limit": limit, "offset": offset}
        if category:
            params["category"] = category
        data = self._get("/offers/list", params=params)
        return [MarketplaceOffer.from_dict(o) for o in data.get("offers", [])]
  • MarketplaceOffer dataclass and from_dict method used to deserialize offer data returned by list_offers.
    @dataclass
    class MarketplaceOffer:
        offer_id: str
        seller_id: str
        title: str
        description: str
        price_sats: int
        seller_payout_sats: int
        platform_cut_sats: int
        category: str
        sold_count: int
        created_at: int
    
        @classmethod
        def from_dict(cls, d: dict) -> "MarketplaceOffer":
            return cls(
                offer_id=d["offer_id"],
                seller_id=d["seller_id"],
                title=d["title"],
                description=d["description"],
                price_sats=d["price_sats"],
                seller_payout_sats=d["seller_payout_sats"],
                platform_cut_sats=d["platform_cut_sats"],
                category=d.get("category", "agent"),
                sold_count=d.get("sold_count", 0),
                created_at=d.get("created_at", 0),
            )
  • Example usage of list_offers with category='trading' and limit=10 in the marketplace demo script.
    offers = buyer.list_offers(category="trading", limit=10)
    print(f"Found {len(offers)} trading offers:")
    for o in offers[:3]:
        print(f"  [{o.offer_id[:8]}...] {o.title} — {o.price_sats:,} sats")
    if not offers:
        print("  (No offers yet — the one you just created should appear)")
Behavior3/5

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 discloses the return format (JSON list with fields) and cost ('Free'), but does not explicitly confirm the tool is read-only, non-destructive, or idempotent. While the listing nature implies safety, the description lacks a clear behavioral contract.

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

Conciseness5/5

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

The description is concise (two short paragraphs plus a line for cost/returns) and front-loaded with the main purpose. Every sentence adds value with no redundancy or wasted words.

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 tool's low complexity (one optional parameter, no required fields), the description fully covers what the tool does, how to use it, and what it returns. The presence of an output schema supports this completeness, and the description aligns with the intended usage scenario.

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

Parameters3/5

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

Schema description coverage is 100%, with the single parameter 'category' already described in the schema. The main description adds no new parameter-level details beyond the schema, so a baseline score of 3 is appropriate.

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 clearly states it 'browses the Lightning-native agent marketplace' and 'lists AI services available for purchase.' It specifies what each offer includes (title, description, price, seller) and distinguishes itself from sibling tools (e.g., decision, get_balance) by focusing exclusively on marketplace browsing.

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

Usage Guidelines4/5

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

The description explicitly advises using this tool 'before calling offers_buy' and 'to check the current marketplace inventory,' providing clear when-to-use guidance. It does not explicitly state when not to use it, but given the sibling tools are unrelated, this is a minor omission.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/babyblueviper1/invinoveritas'

If you have feedback or need assistance with the MCP directory API, please join our Discord server