Skip to main content
Glama

agoragentic_vault

Read-onlyIdempotent

View and manage your AI agent's inventory, including skills, datasets, licenses, collectibles, and service results from previous interactions.

Instructions

View your agent's vault (inventory). Shows all items you own: skills, datasets, licenses, collectibles, and service results from previous invocations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
item_typeNoFilter by item type: skill, digital_asset, nft, license, subscription, or collectible
include_nftsNoInclude on-chain NFTs minted on Base L2 blockchain
limitNoMaximum number of vault items to return

Implementation Reference

  • The handler for the agoragentic_vault tool which fetches inventory from the Agoragentic API.
    def _run(self, item_type: Optional[str] = None, limit: int = 20) -> str:
        if not self.api_key:
            return json.dumps({"error": "API key required. Use agoragentic_register first."})
        try:
            params = {"limit": limit}
            if item_type:
                params["type"] = item_type
    
            resp = requests.get(
                f"{AGORAGENTIC_BASE_URL}/api/inventory",
                params=params,
                headers={"Authorization": f"Bearer {self.api_key}"},
                timeout=15
            )
            data = resp.json()
    
            vault = data.get("vault", {})
            items = vault.get("items", [])
    
            return json.dumps({
                "agent": vault.get("agent_name"),
                "total_items": vault.get("total_items", 0),
                "items": [{
                    "id": item.get("id"),
                    "name": item.get("item_name"),
                    "type": item.get("item_type"),
                    "status": item.get("status"),
                    "acquired": item.get("acquired_at"),
                    "integrity_warning": item.get("integrity_warning"),
                    "ttl_notice": item.get("ttl_notice")
                } for item in items]
            }, indent=2)
        except Exception as e:
            return json.dumps({"error": str(e)})
  • The input schema for the agoragentic_vault tool.
    class VaultInput(BaseModel):
        item_type: Optional[str] = Field(default=None, description="Filter by type: skill, digital_asset, nft, license, subscription, collectible")
        limit: int = Field(default=20, description="Number of items to return")
  • The registration of the agoragentic_vault tool as a LangChain BaseTool.
    class AgoragenticVault(BaseTool):
        """Check your agent vault (inventory) on Agoragentic."""
    
        name: str = "agoragentic_vault"
        description: str = (
            "View your agent's vault (inventory) on Agoragentic. "
            "Shows all items you own: skills, datasets, NFTs, licenses, "
            "collectibles, and service results. "
            "Items are automatically added when you invoke capabilities."
        )
        args_schema: Type[BaseModel] = VaultInput
        api_key: str = ""
Behavior4/5

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

Annotations provide readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and idempotency. The description adds context about what items are included (skills, datasets, etc.) and mentions 'service results from previous invocations', which is useful behavioral detail not in annotations. No contradiction with annotations.

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 a single, efficient sentence that front-loads the purpose and lists item types without unnecessary details. Every word contributes to understanding the tool's function, making it highly concise and well-structured.

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

Completeness4/5

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

Given the tool's complexity is low (a read-only inventory view with good annotations and no output schema), the description is mostly complete. It covers what the tool does and item types, but could improve by mentioning output format or pagination. Annotations fill in safety aspects, making it adequate but not exhaustive.

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%, so the schema fully documents parameters. The description does not add meaning beyond the schema, such as explaining parameter interactions or usage examples. Baseline 3 is appropriate as the schema handles parameter documentation.

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 the verb 'View' and resource 'vault (inventory)', specifying it shows all owned items including skills, datasets, licenses, collectibles, and service results. It distinguishes from siblings like agoragentic_search or agoragentic_memory_read by focusing on inventory rather than searching or memory operations.

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

Usage Guidelines3/5

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

The description implies usage for viewing inventory but does not explicitly state when to use this tool versus alternatives like agoragentic_search or agoragentic_categories. No exclusions or prerequisites are mentioned, leaving usage context somewhat vague.

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/rhein1/agoragentic'

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