bounty-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | Optional GitHub token sent as `Authorization: Bearer …` to GitHub. Raises the search limit from 10 to 30 requests/min. A classic or fine-grained token with no extra scopes is enough to search public issues. Results are limited to public repositories whatever the token can access. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_github_bountiesA | Search open GitHub issues labelled "bounty" or Algora's "💎 Bounty", newest first. Amounts are parsed heuristically from the title, labels and body and may be missing or wrong. |
| search_opire_rewardsA | List open rewards from Opire (api.opire.dev), sorted by amount (unknown amounts last), then newest first. The API returns a small list and ignores query parameters, so keyword and amount filtering is done locally. |
| search_bountiesA | Search GitHub and Opire concurrently, dedupe by URL, and sort by amount (unknown amounts last), then newest first. If a source fails, results from the others are still returned with a warning. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The two source-specific tools (search_github_bounties, search_opire_rewards) are clearly distinct, but search_bounties is an aggregator that overlaps functionally with both. Descriptions do explain the difference (combined dedupe vs. per-source), which saves it from being truly confusing, but an agent must read carefully to decide whether to call the aggregate or the individual sources.
All three names are snake_case with the same verb 'search_', forming a predictable pattern. The minor deviation is that search_bounties lacks a source qualifier even though it is a superset of the other two, which makes it slightly ambiguous against search_github_bounties.
Three tools for a narrowly scoped bounty-discovery server is reasonable and each has a defensible role. The only inefficiency is that the aggregate tool largely subsumes the two source-specific ones, so the effective surface is closer to one-and-a-half tools.
The server covers discovery/search only: no detail lookup for a specific bounty, no filtering parameters exposed (keyword/amount filtering is done internally for Opire), and no pagination or repo-scoped search. Agents can work around this by using the returned URLs, but the surface stops at listing.