GitHub Capability Router (666 repos, 96.4% token savings) & 5-Vector Prompt-Injection Firewall.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 8 tools
Each tool has a clearly distinct purpose: browsing categories, searching capabilities, retrieving project details, comparing projects, commercial info, provisioning keys, reporting outcomes, and safety scanning. Overlap between browse_categories and search_capabilities is resolved by their descriptions, and commercial tools are separated by pricing catalog vs. API-key provisioning.
All tool names follow a consistent snake_case verb_noun pattern, such as browse_categories, get_project_details, and scan_repository_safety. There are no mixed casing conventions or vague standalone verbs.
Eight tools is well-scoped for a capability discovery and evidence platform. Each tool maps to a distinct workflow step without obvious redundancy or bloat.
The surface covers the main lifecycle: category browsing, capability search, project detail/comparison, commercial access, safety scanning, and outcome reporting. Minor gaps exist around API key status/usage management and explicit category-filtered project listing, but core workflows are covered.
List all 15 multi-dimensional capability categories and their subcategories.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Compare multiple candidate projects side-by-side across match type, OS support, license, and limitations.
| Name | Required | Description | Default |
|---|---|---|---|
| projects | Yes | Array of project IDs or canonical names to compare |
Retrieve the CapabilityMap Nexus commercial pricing catalog (€0 Community, €19/mo Pro, €99/mo Enterprise, €149/mo Partner) with features, ROI stats, and PayPal checkout URLs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Retrieve full provenance, evidence excerpts, OS compatibility, and limitations for a project.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project ID (e.g. proj-rufus) or canonical_name (e.g. pbatard/rufus) |
Instantly provision a free trial API key with 100 free query credits for CapabilityMap Nexus, including Pro (€19/mo) and Enterprise (€99/mo) upgrade links.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | Requested tier (default: trial) | |
| No | Developer or agent email for receipt / key assignment (optional) |
Report real-world agent or developer execution outcome (worked, partial, failed) to update evidence confidence.
| Name | Required | Description | Default |
|---|---|---|---|
| outcome | Yes | ||
| agent_id | No | ||
| goal_query | Yes | ||
| project_id | No | ||
| canonical_name | No | ||
| environment_notes | No |
Scan any GitHub repository or MCP server for prompt-injection vulnerabilities and generate a dynamic verified Markdown shield badge.
| Name | Required | Description | Default |
|---|---|---|---|
| repo | Yes | GitHub repo slug (e.g. owner/repo) or full GitHub URL |
Problem-oriented capability search. Decomposes a technical goal into concepts, category routes, multi-component solution paths, and ranked evidence-backed software projects.
| Name | Required | Description | Default |
|---|---|---|---|
| os | No | Host or target OS filter (Windows, Linux, Android, macOS, any) | |
| goal | Yes | Technical problem or capability goal to accomplish | |
| license | No | License filter (open_source, permissive, any) | |
| verified_only | No | Only return evidence_checked or verified projects | |
| include_partial | No | Include partial and multi-component matches |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_commercial_tiersprovision_api_keyscan_repository_safetybrowse_categoriescompare_projectsget_project_detailsreport_outcomesearch_capabilitiesReal-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
BYOK AI router & FinOps control plane: audit token waste, check tool safety, and rank models.
Add one secure layer between your agents and this server.
