h1-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| H1_MCP_ENV | No | Path to the shared credentials file. | ~/.config/h1-mcp/env |
| H1_MCP_HOME | No | Directory for the default file. | ~/.config/h1-mcp |
| H1_USERNAME | Yes | HackerOne username (wins over the file). | |
| H1_API_TOKEN | Yes | HackerOne API token. |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_programsA | List HackerOne programs you can access. Filter by bounty eligibility, submission state or a handle/name substring. Returns handles to feed the other tools. |
| get_programB | Program metadata and policy (truncated). Set flags to also include structured scope and/or scope exclusions in one call. |
| get_structured_scopesC | In-scope assets for a program: identifier, type, bounty eligibility and max severity. |
| get_scope_exclusionsC | Report categories the program excludes from rewards (out-of-scope classes). |
| check_in_scopeA | Decide whether an asset (host, URL, IP or CIDR entry) is covered by a program's structured scope. Returns every matching scope entry plus the program's exclusions as caveats. |
| hacktivity_searchB | Search disclosed reports (dedup / prior art). |
| search_disclosed_reportsC | Disclosed reports for one program (dedup scoped to the program you are hunting). |
| my_reportsB | Your own submitted reports (state, severity, bounty). Pass |
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 8 tools
There is meaningful overlap: get_program can optionally return structured scope and exclusions, duplicating get_structured_scopes and get_scope_exclusions, and hacktivity_search vs search_disclosed_reports both search disclosed reports. Descriptions clarify scope (global Lucene vs per-program) and intent, but an agent can reasonably hesitate between the program-metadata tool with flags and the dedicated scope tools.
Most tools use a readable snake_case verb_noun pattern (list_programs, get_program, get_structured_scopes, check_in_scope). However hacktivity_search reverses the order compared to search_disclosed_reports, and my_reports is a possessive noun rather than a verb, creating mixed conventions.
Eight tools is a well-sized surface for the HackerOne domain, comfortably within the 3-15 range. There is slight redundancy because get_structured_scopes and get_scope_exclusions overlap with get_program's flags, so not every tool strictly earns an independent place.
The set covers program discovery, policy/scope lookup, scope checking, disclosed-report research, and a user's own reports—core hunting workflows. Gaps are minor for a read-oriented server: no report submission, no direct get-by-ID for disclosed reports, and program policy is noted as truncated.