taken
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TAKEN_CACHE_DIR | No | Override the cache directory for API responses (default: ~/.cache/taken) | ~/.cache/taken |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_issueA | Check whether a GitHub issue is already taken. Verdicts: GO (free to volunteer), TAKEN (spoken for: closed, open PR, or assignee), CAUTION (soft signal: someone expressed interest, the repo bans AI contributions, or the repo looks stale). The payload also carries Error payloads carry Args: owner: repository owner login repo: repository name issue_number: issue number to check me: your GitHub login; your own comments are ignored in the claimant scan graphql: force the GraphQL fetch path instead of the automatic choice persistent_session: force the persistent-session GraphQL path instead of the automatic one pr_idle_days: stale-claim decay threshold for idle linked PRs (default 90) claim_silence_days: stale-claim decay threshold for simple issues (default 7) claim_silence_complex_days: stale-claim decay threshold for complex issues (default 14) |
| scan_repoA | Scan a repository's open issues and recommend the GO ones. Results are ordered GO first, then CAUTION, then TAKEN, so the best
candidates to volunteer for come first. Error payloads carry Args: owner: repository owner login repo: repository name limit: max open issues to check (default 20) label: only consider open issues carrying this label me: your GitHub login; your own comments are ignored in the claimant scan pr_idle_days: stale-claim decay threshold for idle linked PRs (default 90) claim_silence_days: stale-claim decay threshold for simple issues (default 7) claim_silence_complex_days: stale-claim decay threshold for complex issues (default 14) |
| discover_candidatesB | Discover top open-source contribution candidates. Searches GitHub for good-first-issue style issues, runs taken's full
verification on each, and returns the ranked candidates. Each result
carries Error payloads carry Args: limit: max candidates to return (default 10) language: only consider repos in this language label: issue label to search (defaults to good-first-issue style labels) min_contributors: only consider repos with at least this many contributors in the last 90 days me: your GitHub login; your own comments are ignored in the claimant scan pr_idle_days: stale-claim decay threshold for idle linked PRs (default 90) claim_silence_days: stale-claim decay threshold for simple issues (default 7) claim_silence_complex_days: stale-claim decay threshold for complex issues (default 14) |
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 three tools operate at clearly distinct scopes: check_issue inspects a single issue, scan_repo scans one repository's open issues, and discover_candidates searches GitHub globally. An agent can trivially select the right tool based on whether it has an issue number, a repo, or neither.
All three names follow a clean verb_noun snake_case pattern (check_issue, scan_repo, discover_candidates). The verbs are also semantically meaningful and distinct, reinforcing the scope separation.
Three tools is on the thin side but each maps to a genuinely different granularity (single issue, single repo, global discovery), so none is redundant. The focused domain justifies the small surface.
The single→repo→global progression covers the core workflow of finding and vetting contribution targets, with consistent error and metadata handling across tools. Minor gaps exist (e.g. no batch check of an explicit issue list or PR-level inspection), but agents can work around them via scan_repo.