TargetFinder
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | Optional GitHub token that raises the GitHub compare API budget from 50/h to 5000/h. | |
| TARGETFINDER_DB | No | Path to the TargetFinder database. | |
| TARGETFINDER_API_HOST | No | Host used by the local HTTP API. | |
| TARGETFINDER_API_PORT | No | Port used by the local HTTP API. | |
| TARGETFINDER_DATA_DIR | No | Directory used for TargetFinder's database and logs. | |
| TARGETFINDER_SWEEP_DIR | No | Directory where sweep reports are written. | |
| TARGETFINDER_ENABLE_IMMUNEFI | No | Set to 1 to opt in to collecting Immunefi data; off by default. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| guideA | How to choose among these tools; id format; filter vocabulary. |
| statusB | Database counts, last sync, collectors and their last successful run. |
| find_programsC | Program discovery with combined filters. |
| get_programB | One program by id, handle or unambiguous name (full object). |
| program_briefB | One-screen summary: rewards, fee, competition, scope counts, recent activity, payouts, sample eligible targets. |
| list_targetsC | Targets of one program with scores. |
| search_targetsC | Search targets across all programs. |
| find_program_by_targetC | Which program(s) list a domain / URL / repo / wildcard. |
| recent_target_changesD | Target changes (page mode or after_id cursor). |
| recent_repo_pushesC | Source-repository pushes (page mode or after_id cursor). Compare links, no code. |
| leadsD | Programs in one lead tier. |
| rankingsD | One ranked page of a view. |
| program_payoutsC | Payout facts, windows, signals and labels for one program. |
| program_historyB | Event history (program/scope/rewards/fees/status/repositories) for one program, or all programs when program_id is omitted. |
| watchlist_new_targetsC | New in-scope targets for a list of programs since a timestamp. |
| export_targetsC | Bounded export (max 500 rows) of current targets. |
| list_filtersC | Observed filter values (platforms, tags, target types) and the fixed vocabularies. |
| run_sweepB | Run the standing sweep report and return the markdown. |
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 18 tools
Most tools target distinct resources and actions: program lookup, target listing/search, repository pushes, filters, and exports are clearly separated. Some overlap remains between find_programs and leads, between program_brief and program_payouts, and between recent_target_changes and watchlist_new_targets, but the guide tool and descriptions help disambiguate.
All names use snake_case, but conventions are mixed: verb-led names (find_programs, get_program, list_targets, search_targets) coexist with noun-led or bare-noun names (guide, status, leads, rankings, program_brief, program_history). The names remain readable, but there is no single predictable verb_noun pattern.
Eighteen tools is somewhat heavy for a program/target discovery server, with several meta or shortcut tools (guide, status, list_filters, leads) that could potentially be folded into others. It is not excessive for the domain's breadth, but it sits above the ideal 3–15 range.
The surface covers discovery, detailed program summaries, target listing/search, history, change feeds, rankings, filters, exports, and sweeps, so core read-only workflows are well supported. Minor gaps exist around watchlist management (only watchlist_new_targets is present, with no list/add/remove operations) and direct target-detail lookup.