Bring Scribe
to LlamaIndex
Learn how to connect Scribe to LlamaIndex and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Scribe MCP Server?
Connect your Scribe organization to any AI agent and access your process documentation library through natural conversation.
What you can do
- Full Search — Search across all Scribes and Knowledge Pages simultaneously.
- Filtered Search — Search only guides or only pages for targeted results.
- Team Scoping — Find documents within a specific team for departmental queries.
- Date Filtering — Search by creation date range or get recent documents.
- Teams — List all teams and their documents for content auditing.
- Statistics — Get an overview of your documentation footprint.
How it works
1. Subscribe to this server
2. Enter your Scribe API key (Enterprise Grid or Global plan required)
3. Start searching documentation from Claude, Cursor, or any MCP client
Who is this for?
- Knowledge Managers — quickly find and audit process documentation.
- Support Teams — retrieve step-by-step guides for customer assistance.
- Operations Leads — monitor documentation activity across teams.
Built-in capabilities (10)
Verify Scribe API connectivity
Get documentation statistics
Get documents created in the last 30 days
Useful for auditing team documentation. Get all documents for a specific team
List all teams in your Scribe organization
Dates should be in YYYY-MM-DD format. Search documents by creation date range
Search documents within a specific team
Search across all Scribes and Pages
Search only Knowledge Pages
Search only Scribe guides
Why LlamaIndex?
LlamaIndex agents combine Scribe tool responses with indexed documents for comprehensive, grounded answers. Connect 10 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 Scribe tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain Scribe tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query Scribe, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what Scribe tools were called, what data was returned, and how it influenced the final answer
Scribe in LlamaIndex
Scribe and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Scribe 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 Scribe in LlamaIndex
The Scribe 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 10 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
Scribe for LlamaIndex
Every tool call from LlamaIndex to the Scribe MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I search only for step-by-step guides?
Yes! Use search_scribes to search exclusively for Scribe guides, or search_pages for Knowledge Pages only.
Do I need an Enterprise plan to use this?
Yes, the Scribe Search & Retrieval API is available on Enterprise Grid and Global plans. Contact Scribe sales for API access.
Can I find documents by a specific team?
Yes! First use list_teams to see available teams and their IDs, then use search_by_team or get_team_documents with the team ID.
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 Scribe 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