pickfit

BrowseLocal AI tools

mcp-inicio-ia

MCP server indexing Markdown docs in SQLite FTS5 with notes and Ollama assistant.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.12
  • System packages: SQLite with FTS5
  1. clone repository to /tmp/mcp-inicio-ia

    git clone https://github.com/em4nu3i69dll/mcp-inicio-ia.git /tmp/mcp-inicio-ia
  2. install requirements and package with pip

    cd /tmp/mcp-inicio-ia && python3 -m pip install -r requirements.txt && python3 -m pip install --no-deps .

Check that it works

cd /tmp/mcp-inicio-ia && python3 -m mcp_inicio --help

The output should contain “usage: mcp-inicio”.

First thing to try

cd /tmp/mcp-inicio-ia && python3 -m mcp_inicio preparar

From the project folder, run python3 -m mcp_inicio preparar to index the documents first.

What it does

  • Search local documents
    How to use it
    1. Run python3 -m mcp_inicio preparar in the project folder to index the documents.
    2. Run python3 -c "from mcp_inicio.almacen import Almacen; import json; print(json.dumps(Almacen('.').buscar('<your text>'), ensure_ascii=False, indent=2))" to get matching fragments.
    Tested
  • Save and look up your notes
    How to use it
    1. Write your note text into a file.
    2. Run python3 -m mcp_inicio nota --titulo "<title>" --archivo <file> to save it.
    3. Run python3 -c "from mcp_inicio.almacen import Almacen; import json; print(json.dumps(Almacen('.').notas(), ensure_ascii=False, indent=2))" to list saved notes.
    Tested
  • Read an indexed document by its ID
    How to use it
    1. Run python3 -m mcp_inicio preparar to index the documents.
    2. Run `python3 -c "from mcp_inicio.almacen import Almacen; import json; a=Almacen('.'); docs=a.listar(); did=docs['documentos'][0]['id']; print('DOC_ID:'+did); print(json.dumps(a.leer(did), ensure_ascii
    Tested
  • Ask a local assistant through Ollama
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 3 of 4 features work
  4. Works offline

macOS: the project says it runs there; pickfit hasn’t tried it.

Good for

  • search indexed documents by relevance
  • read indexed document by ID with pagination
  • save user note from a text file
  • expose server context via MCP resource
  • prepare research query from a question

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.0.0

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.