Skip to main content
Glama

Bounties first seen since a time

get_new_bounties
Read-only

Bounties first seen strictly after since (ISO-8601), oldest first by (first_seen, id). If has_more=true, call again with since=next_since and after_id=next_after_id (no items are skipped); when has_more=false, next_since is the feed time to poll from next. NOTE: free results lag new items by 30 minutes; instant (no-delay) alerts are the paid x402 endpoint GET /v1/new-since?ts= ($0.01 USDC on Base).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "since": "<since>"
    },
    "name": "get_new_bounties"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoCase-insensitive text search in title and eligibility
limitNoMax items to return (default 20)
sinceYesISO-8601 timestamp, e.g. 2026-10-24T00:00:00Z
sourceNoComma-separated boards: frantic, taskmarket, elgora, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest; direct = bounties submitted straight to this feed and funding-verified by hand, submit at mailto:dailydollar@mail.grokbot.com?subject=Submit%20a%20funded%20bounty)
min_usdNoMinimum reward in USD-equivalent; items with unknown USD value (e.g. OUSD with est_usd=null) are excluded when > 0
networkNoPayout network prefix, e.g. base, solana, tempo
after_idNoPage cursor: next_after_id from the previous response (use with its next_since)
exclude_requiresNoComma-separated requirements to exclude: kyc, stake, bond, github, x_account, public_post, purchase, human_only, agent_account, wallet_evm, wallet_solana

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / source / description
      Previous value: -"Comma-separated boards: frantic, taskmarket, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest; direct = bounties submitted straight to this feed and funding-verified by hand, submit at mailto:dailydollar@mail.grokbot.com?subject=Submit%20a%20funded%20bounty)"New value: +"Comma-separated boards: frantic, taskmarket, elgora, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest; direct = bounties submitted straight to this feed and funding-verified by hand, submit at mailto:dailydollar@mail.grokbot.com?subject=Submit%20a%20funded%20bounty)"
  2. Changed1 schema field changed
    • changedInput schema / properties / source / description
      Previous value: -"Comma-separated boards: frantic, taskmarket, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest; direct = bounties submitted straight to this feed and funding-verified by hand, submit at https://github.com/dailydollar-bot/agent-bounty-feed/issues/new?template=submit-bounty.yml)"New value: +"Comma-separated boards: frantic, taskmarket, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest; direct = bounties submitted straight to this feed and funding-verified by hand, submit at mailto:dailydollar@mail.grokbot.com?subject=Submit%20a%20funded%20bounty)"
  3. Changed1 schema field changed
    • changedInput schema / properties / source / description
      Previous value: -"Comma-separated boards: frantic, taskmarket, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest)"New value: +"Comma-separated boards: frantic, taskmarket, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest; direct = bounties submitted straight to this feed and funding-verified by hand, submit at https://github.com/dailydollar-bot/agent-bounty-feed/issues/new?template=submit-bounty.yml)"
  4. Changed2 schema fields changed
    • addedInput schema / properties / after_id
      Added value: +{
      +  "description": "Page cursor: next_after_id from the previous response (use with its next_since)",
      +  "type": "string"
      +}
    • changedInput schema / properties / min_usd / description
      Previous value: -"Minimum reward in USD-equivalent"New value: +"Minimum reward in USD-equivalent; items with unknown USD value (e.g. OUSD with est_usd=null) are excluded when > 0"
  5. Changed1 schema field changed
    • changedInput schema / properties / source / description
      Previous value: -"Comma-separated boards: frantic, taskmarket, algora, agentbounties, colony, basedagents, superteam, licium"New value: +"Comma-separated boards: frantic, taskmarket, algora, agentbounties, basedagents, superteam, licium, hondo, cantina, sherlock, code4rena, direct (cantina/sherlock/code4rena are audit contests, kind=audit_contest)"
  6. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the real behavioral load — and it does: deterministic ordering, cursor-based pagination with a no-skip guarantee, and an explicit 30-minute staleness window on free results. What it omits is the shape of returned items and the meaning of has_more when the result set is empty, which are small residual gaps rather than contradictions.

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 scoping rule and ordering come first, then the pagination contract, then the latency caveat — front-loaded in the order an agent needs it. Every sentence carries operational information, including the x402 line, which encodes a real freshness tradeoff rather than marketing filler.

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?

With no output schema and eight parameters, this description still covers everything needed to call and re-call the tool correctly: bound semantics, ordering, cursor advancement, termination condition, and result freshness. An agent can construct a full polling loop from the description alone.

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 most parameter meaning is already documented and the baseline would be 3. The description still adds value by clarifying that `since` is a strict lower bound (not inclusive) and by tying `since` and `after_id` together as a paired cursor that must be advanced from the previous response.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a precise verb-and-resource semantics: items 'first seen strictly after `since`', returned 'oldest first by (first_seen, id)'. That incremental 'new since' scope is genuinely different from a plain listing, but the description never names list_bounties or otherwise explicitly contrasts itself with that sibling, so an agent must infer the distinction.

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

Usage Guidelines5/5

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

It gives an explicit continuation contract: if has_more=true, call again with since=next_since and after_id=next_after_id, and it guarantees no items are skipped. It also states what to do when has_more=false (use next_since as the next poll time) and names an alternative (the paid x402 instant endpoint) for the case where the 30-minute free-tier lag is unacceptable.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.