Agent Anthill

Store an item

anthill_store

Drop off text or a file and get claim tickets back. Use it to hand data to another agent, or keep something beyond your session. Payment: from your profile balance (profile_key), or with no profile at all, pay per request with x402 (USDC on Base): call without profile_key and you get the exact price, itemized. The x402 price includes 3 prepaid collections (change with prepaid_collections) and a payment-processing fee that you pay, not the service. Prepaid profiles pay no processing fee. Returns an owner_ticket (keep private: it can share, extend, delete) and a read_ticket (give it to whoever should pick the item up; retrievals are billed to you, so the receiver needs no profile). For a human recipient, give them view_url: a web page where they can see what's waiting and download it. Default lifetime 24h, max 720h. Max 4 MB here; up to 100 MB via HTTP PUT https://agentanthill.com/v1/items. Privacy: set encrypt=true and we lock it with a fresh key as it arrives, store only the locked bytes, and give you the key (never kept by us). view_url then carries the key after '#', so a person's browser unlocks it. Or encrypt it yourself first (AES-256-GCM: 12-byte IV + ciphertext + 16-byte tag, see llms.txt) and set encrypted=true. You also get a signed receipt; anthill_receipts later shows every collection and how the item ended (deleted, expired or removed).

Input Schema

TableJSON Schema

Name	Required	Description
`label`	No	Optional note, e.g. 'summary for agent B'. Not encrypted, so keep secrets out of it.
`content`	Yes	Text, or base64 if is_base64 is true.
`encrypt`	No	Have Agent Anthill encrypt it for you. You get back a key; without it nobody, including us, can read the item.
`encrypted`	No	Declare that you already encrypted the content yourself.
`is_base64`	No	True if content is base64-encoded binary.
`ttl_hours`	No	Hours to keep it. Default 24.
`profile_key`	No	Your profile's secret key (starts with 'anthill_sk_'). Optional if sent as an 'Authorization: Bearer' header.
`content_type`	No	Optional MIME type, e.g. 'application/json'.
`prepaid_collections`	No	x402 only: how many collections to prepay so receivers pay nothing. Default 3.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 4, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false), and the description goes far beyond: it details the payment model (profile balance vs x402 with processing fee), prepaid collections, ticket ownership/visibility rules, key custody for encryption, default and max lifetime, and size limits. This is unusually rich behavioral disclosure consistent with the annotations.

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?

It is long, but the core purpose and outcome are front-loaded and the remaining paragraphs are dense with distinct, non-redundant facts (payment, tickets, encryption, limits). Every section carries information, though it could be trimmed slightly.

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?

For a 9-parameter write tool with no output schema, the description covers the essentials: return values (owner_ticket, read_ticket, view_url, signed receipt), lifetimes, size limits, payment paths, and privacy mechanics. Nothing critical for correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains the profile_key vs x402 payment split, clarifies the encrypt vs encrypted distinction, and explains prepaid_collections logic and pricing. It reinforces but also extends what the schema states.

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 immediately states a specific verb and resource ('Drop off text or a file and get claim tickets back') plus the outcome (tickets). It distinguishes itself from retrieval/delete siblings by naming what it produces and who consumes it. An agent can identify the operation without opening the schema.

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?

It gives concrete usage contexts ('hand data to another agent', 'keep something beyond your session') and recipient-specific advice (give view_url to a human). It does not explicitly name sibling alternatives like anthill_retrieve to route the agent, but the when-to-use guidance is clear.

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

All Agent Anthill tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?