4,000+ servers built on vurb.ts
Vinkius

PhotoPrism MCP Server for LlamaIndexGive LlamaIndex instant access to 7 tools to Create Oauth Token, Get Oauth Authorize, Get Oauth Userinfo, and more

MCP Inspector GDPR Free for Subscribers

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add PhotoPrism as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Ask AI about this MCP Server for LlamaIndex

The PhotoPrism MCP Server for LlamaIndex is a standout in the Productivity category — giving your AI agent 7 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
python
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to PhotoPrism. "
            "You have 7 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in PhotoPrism?"
    )
    print(response)

asyncio.run(main())
PhotoPrism
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About PhotoPrism MCP Server

Connect your self-hosted PhotoPrism instance to any AI agent to interact with your personal media collection through natural language.

LlamaIndex agents combine PhotoPrism tool responses with indexed documents for comprehensive, grounded answers. Connect 7 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.

What you can do

  • Advanced Search — Query your library using keywords, colors, or dates with the search_photos tool.
  • Visual Previews — Generate direct URLs for thumbnails in various sizes using get_thumbnail_url.
  • Video Streaming — Access streaming links for your stored videos with get_video_url.
  • OAuth Management — Handle authentication tokens and user information securely with create_oauth_token and get_oauth_userinfo.

The PhotoPrism MCP Server exposes 7 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 7 PhotoPrism tools available for LlamaIndex

When LlamaIndex connects to PhotoPrism through Vinkius, your AI agent gets direct access to every tool listed below — spanning media-management, photo-library, metadata-search, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

create

Create oauth token on PhotoPrism

Create an OAuth2 token

get

Get oauth authorize on PhotoPrism

Get OAuth2 Authorization

get

Get oauth userinfo on PhotoPrism

Get OAuth2 UserInfo

get

Get thumbnail url on PhotoPrism

Get a thumbnail image URL for a photo

get

Get video url on PhotoPrism

Get a video streaming URL

revoke

Revoke oauth token on PhotoPrism

Revoke an OAuth2 token

search

Search photos on PhotoPrism

Search for photos in PhotoPrism

Connect PhotoPrism to LlamaIndex via MCP

Follow these steps to wire PhotoPrism into LlamaIndex. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai
02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token
03

Run the agent

Save to agent.py and run: python agent.py
04

Explore tools

The agent discovers 7 tools from PhotoPrism

Why Use LlamaIndex with the PhotoPrism MCP Server

LlamaIndex provides unique advantages when paired with PhotoPrism through the Model Context Protocol.

01

Data-first architecture: LlamaIndex agents combine PhotoPrism tool responses with indexed documents for comprehensive, grounded answers

02

Query pipeline framework lets you chain PhotoPrism tool calls with transformations, filters, and re-rankers in a typed pipeline

03

Multi-source reasoning: agents can query PhotoPrism, a vector store, and a SQL database in a single turn and synthesize results

04

Observability integrations show exactly what PhotoPrism tools were called, what data was returned, and how it influenced the final answer

PhotoPrism + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the PhotoPrism MCP Server delivers measurable value.

01

Hybrid search: combine PhotoPrism real-time data with embedded document indexes for answers that are both current and comprehensive

02

Data enrichment: query PhotoPrism to augment indexed data with live information before generating user-facing responses

03

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying PhotoPrism for fresh data

04

Analytical workflows: chain PhotoPrism queries with LlamaIndex's data connectors to build multi-source analytical reports

Example Prompts for PhotoPrism in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with PhotoPrism immediately.

01

"Search for photos of 'mountains' taken in 2023."

02

"Get a high-resolution thumbnail for the photo with hash 7af8b9c0."

03

"Show me my PhotoPrism account information."

Troubleshooting PhotoPrism MCP Server with LlamaIndex

Common issues when connecting PhotoPrism to LlamaIndex through Vinkius, and how to resolve them.

01

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

PhotoPrism + LlamaIndex FAQ

Common questions about integrating PhotoPrism MCP Server with LlamaIndex.

01

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.
02

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query PhotoPrism tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
03

Does LlamaIndex support async MCP calls?

Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.

Explore More MCP Servers

View all →