Bring Video Interviewing
to LlamaIndex
Learn how to connect HRBlade to LlamaIndex and start using 6 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the HRBlade MCP Server?
Connect your HRBlade account to any AI agent and manage asynchronous video interviews through natural conversation.
What you can do
- Interview Templates — List all interview templates and create new ones with custom questions, time limits, and instructions
- Candidate Invitations — Send video interview invitations to candidates by email with personalized details
- Candidate Management — Browse all candidates in your pipeline and inspect individual profiles with status
- Response Review — List all submitted video responses to review candidate answers and evaluate performance
How it works
1. Subscribe to this server
2. Enter your HRBlade API Key from your account settings
3. Start managing interviews from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Recruiters — create interview templates, send invitations, and review video responses without switching to the dashboard
- Hiring Managers — evaluate candidate responses and track pipeline progress through AI
- HR Teams — scale asynchronous interviewing and manage high-volume candidate screening
Built-in capabilities (6)
Pass data as a JSON string. Create a new interview template
Get specific candidate details
List all recruiting candidates
List all candidate video responses
List all interview templates
Pass data as a JSON string. Send an invitation to a candidate
Why LlamaIndex?
LlamaIndex agents combine HRBlade tool responses with indexed documents for comprehensive, grounded answers. Connect 6 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine HRBlade tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain HRBlade tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query HRBlade, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what HRBlade tools were called, what data was returned, and how it influenced the final answer
HRBlade in LlamaIndex
HRBlade and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect HRBlade to LlamaIndex through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for HRBlade in LlamaIndex
The HRBlade MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
HRBlade for LlamaIndex
Every tool call from LlamaIndex to the HRBlade MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I create an interview template and send invitations to candidates?
Yes. Use create_interview with a JSON payload containing the title, description, and an array of questions. Then use send_interview_invitation with the candidate's email, first name, last name, and the interview ID. The candidate will receive an email with a link to record their video responses.
Can I review all video responses submitted by candidates?
Yes. The list_interview_responses tool retrieves all submitted video responses with candidate details, interview template reference, and submission timestamps. Use get_candidate_details to inspect a specific candidate's full profile and response history.
How does asynchronous video interviewing work with HRBlade?
HRBlade enables one-way video interviews where candidates record responses at their own pace. You create a template with questions, send an invitation, and the candidate records video answers through a web link. You can then review all responses asynchronously without scheduling live calls. Use list_interviews to see all templates and list_candidates to track your pipeline.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query HRBlade tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp