Find your files with natural language and ask questions.
Find your files with natural language and ask questions. That is what the π§ archive agent mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
([If you can't see the diagram below, view it on Mermaid.live](https://mermaid.live/edit#pako:eNqFU9tu2kAQ_ZXRSnkDamwDiRUhEYcQEmgT6EVqycPanpgV9q61XieQKP_evUBuqtQX5J1z5sycmeGZpCJDEpFc0moNs8WKrzjA0RFMeY61YoLDDauwYBwNUDeJY77CJgow-nOaDL9Lmm6A8gxiUZZMwQUrsD79kgxPEzlcNlUlpKrhRop7A9xBuz2EM5Pp1D7yR40SJVUshW_xApZKUoX5ziDTkuYIY66Y2sF4q5HUdHLnWjmzsrGRXWJJuVGI1w3fMJ4ftB-ZWusmucKtgkukGcraxGfaZg0VSjgrRLqJoOt5Jv5LyMzFrVIEvufty8W23LkpNy4TzBzj1cVcj7eIwBRqo8Ez3UY7aBdU5mgIPzFVQsKSPWEEgTfw97rnVndsbWgCftKdiZQWcJtJbRAyqmhCa7SpyLPXJd42KHf_XqCFXKkLU2RUb0zM7tQUcduZvPl6D_7X2d7ExIpcGpEFKsnwAeErUmmW_dHPMjUe54xH4HW6JuJwmNOtmctecOwE3ePSPqZOXQ
The server publishes 14 tools. What each one is for:
OpenAI β Requires an OpenAI API keyOpenRouter β Requires an OpenRouter API key. Access to 400+ modelsOllama β Requires Ollama running locallyText β - Plaintext: .txt, .md, .markdownDocuments β - ASCII documents: .html, .htm (images not supported)Images β .jpg, .jpeg, .png, .gif, .webp, .bmpTrade β off between cost, speed, and accuracy.**Line β based files (e.g., .txt) use the range of line numbers as referencePage β based files (e.g., .pdf) use the range of page numbers as referenceTask β Default ModelChunk β google/gemini-2.5-flash-liteRerank β google/gemini-2.5-flash-liteConfiguration is passed through the environment: OPENAI_API_KEY, OPENROUTER_API_KEY. Treat anything key-shaped as a real credential β scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Setup follows the usual MCP pattern β install or clone the server, register it in your client's configuration file, restart the client.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. π§ Archive Agent's toolset β OpenAI, OpenRouter, Ollama and 11 more β is a fair guide to whether it matches your workflow. It is maintained by shredEngineer; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live β if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| OpenAI | Requires an OpenAI API key. |
| OpenRouter | Requires an OpenRouter API key. Access to 400+ models. |
| Ollama | Requires Ollama running locally. |
| Text | - Plaintext: .txt, .md, .markdown |
| Documents | - ASCII documents: .html, .htm (images not supported) |
| Images | .jpg, .jpeg, .png, .gif, .webp, .bmp |
| Trade | off between cost, speed, and accuracy.** |
| Line | based files (e.g., .txt) use the range of line numbers as reference. |
| Page | based files (e.g., .pdf) use the range of page numbers as reference. |
| Task | Default Model |
| Chunk | google/gemini-2.5-flash-lite |
| Rerank | google/gemini-2.5-flash-lite |
| Query | google/gemini-2.5-flash |
| Vision | google/gemini-2.5-flash |
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| OPENROUTER_API_KEY | Credential the server authenticates with. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans β semantic web search that returns model-ready content, plus code context.
Answers, not links β delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice β text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox β isolated cloud VMs for actually running the code it writes.
The ML hub in your context window β search models, datasets, papers and run Spaces from the official server.