Loading ToolBench
MCP server for the Intigriti Company API v2.1
32 tools with consistent naming (verb_noun pattern) and complete input schemas. All tools have descriptions (10-100 chars, mostly 20-80). Parameters are typed and described. However, output schemas are not documented in the source code, only input schemas are visible. Error handling is minimal; no recovery guidance or actionable error messages. No tool annotations (readOnlyHint/destructiveHint) despite clear risk classifications. Descriptions are functional but brief, lacking context on when to use each tool or dependencies between them. Composition is sound (each tool does one thing), but chaining information (e.g., programId needed after listing programs) is not always returned.
Get custom fields of a company asset
Get the required skills of a company asset
Get company assets
Get all groups
Get all group submissions
Get all company payouts
Create program update
Delete program update
Output schemas not documented. Only input schemas are visible in source; return types for all 32 tools are undocumented. LLMs cannot plan downstream tool calls or extract required fields without knowing what each tool returns.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Risk classifications are provided in the spec (READ_ONLY, WRITE, DESTRUCTIVE) but not exposed in tool definitions. Agents cannot distinguish safe reads from destructive writes without reading descriptions.
Minimal error handling and no recovery guidance. No evidence of actionable error messages, categorization (retryable vs fatal), or suggestions for next steps. Agents will not know how to recover from failures.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 59 | 2025-06-18+ | v2 |
Get all program updates of a program
Get all program updates (company-wide)
Publish program update
Update program update
Get program detail
[BETA] Import known issues and historical vulnerability reports through this API endpoint.
Get all programs
Get all program payouts
Get all researchers of a program
Get all program submissions
Create payout reward request
Delete reward request
Get reward budget
Get reward request payout
Get all reward requests
Get all possible submission types
[BETA] Add an additional attachment to a submission.
Create one or more company submission bonusses
Export submission as a CSV file
Export submission as a PDF file
Get submission detail
Get all submissions
Update submission state
Get user profile
Descriptions are brief (mostly 20-80 chars) and lack context. No explanation of when to use each tool, dependencies between tools, or what data is returned. E.g., 'Get all submissions' does not explain what fields are in the response or when to call it vs submissions_get.
programs_import_submission has 17 optional parameters with minimal descriptions. No guidance on which are required, dependencies, or valid value ranges. LLMs will struggle to construct valid requests.