About bounty-mcp
bounty-mcp is a stdio MCP server that gives AI agents access to active GitHub coding bounties with verified escrow signals. It supports filtering, skill-based candidate ranking, individual bounty lookup, and aggregate statistics.
Key features
- 01Lists bounties by language and dollar floor
- 02Ranks candidates against a skill set
- 03Returns full bounty records
- 04Reports aggregate bounty statistics
- 05Filters known scam-farm sources
Use cases
- 01Find paid coding tasks by language
- 02Match an agent’s skills to bounties
- 03Review a bounty’s details and status
- 04Track bounty counts and funding
MCP support
The stdio MCP server exposes tools to list and match bounties, retrieve a bounty record, and view aggregate statistics. Its data is sourced from GitHub bounty signals, with an optional remote snapshot URL.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @weiseer/bounty-mcpBOUNTY_MCP_URLOverride remote snapshot URLBOUNTY_MCP_LOCAL_ONLYSkip remote fetchLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
4Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | number | No | |
| language | string | No | e.g. python, typescript, rust, go |
| min_dollars | number | No | minimum bounty $ amount |
| bug_fix_only | boolean | No | |
| exclude_open_pr | boolean | No | |
| exclude_assigned | boolean | No |
Details
From the project README@weiseer/bounty-mcp
Live coding-bounty deal-flow as a stdio MCP server. For AI agents finding paid coding work.
Built by weiseer. Probe P-002.
What it does
Gives AI agents real-time access to verified-escrow GitHub coding bounties — currently sourced from Algora's algora-pbc[bot] escrow signals, filtered for scam-farm noise (SecureBananaLabs / ClankerNation / UnsafeLabs excluded at scan level).
Your agent can:
list_bounties— query the active pool by language, $ floor, bug-fix-onlyfind_matching— given a skill set + $ floor, return ranked candidatesget_bounty— full record for one bountyget_stats— aggregate stats (total, by language, unclaimed, $)
Install
npm install -g @weiseer/bounty-mcp
Use with Claude Desktop / Cursor / Cline / Continue / Windsurf
{
"mcpServers": {
"bounty-mcp": {
"command": "npx",
"args": ["-y", "@weiseer/bounty-mcp"]
}
}
}
Why use this instead of your agent scraping Algora itself
| Agent DIY | bounty-mcp | |
|---|---|---|
| Token cost per call | $0.02–0.06 (scrape + parse + filter) | $0 free / $0.00005 paid |
| Latency | 2–5 seconds | <100ms |
| Scam filter | Agent must dedupe known scam-farms | Built-in (SecureBananaLabs / ClankerNation / UnsafeLabs excluded at source) |
| Cross-PR / cross-claim check | Agent must run timeline queries | Pre-computed |
| Rate limit risk | 10,000 agents scraping → all blocked | Single coordinated upstream client |
What's NOT covered (yet)
- Opire / Polar.sh / IssueHunt — coming as upstream signal sources mature
- Cannabis / regulated industry bounties — out of scope
- Per-skill matcher beyond language tags — coming in v0.2
Schema
See bounties.json in the package. Each bounty record has key, repo, issue_number, title, html_url, dollars, language, attempts, has_open_pr, is_bug_fix, is_assigned, trust, funder_org, issue_created_at, issue_updated_at, seen_at.
Environment
BOUNTY_MCP_URL— override the remote bounty snapshot URL (default:https://oracle.weiseer.com/bounties.json)BOUNTY_MCP_LOCAL_ONLY=1— skip remote fetch, use bundled snapshot only
Related weiseer services
@weiseer/llm-oracle-mcp— LLM provider pricing + availability oracle (P-001)- github.com/weiseer — all weiseer services + status
License
Apache-2.0. Catalog format: MIT.
Roadmap
Probe-pulled. What gets added is what users request via issues.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.