My AI Couldn’t See My Recordsdata — I Constructed a Zero-Dependency MCP Server

. The features had grown too lengthy and the variable names made no sense anymore. Each time I needed suggestions on a file, I finished, opened the chat, copied the entire thing in, and waited. Then went again to the editor, utilized the change, opened the subsequent file, and did it once more.

In some unspecified time in the future I counted. Six information. Eleven pastes. Twenty minutes of switching earlier than I wrote a single new line.

The apparent repair was to offer the AI device direct entry to my challenge folder. That’s once I bumped into MCP — the Mannequin Context Protocol — which is precisely constructed for this. A server runs domestically, exposes instruments, and the AI shopper calls these instruments immediately as a substitute of ready for me to stick issues.

So I checked out current implementations. Most required FastAPI, uvicorn, LangChain, or the official MCP SDK. Earlier than writing a single line of enterprise logic I had 5 packages in my necessities file and a server I wasn’t assured would run on Home windows with out a combat.

I stepped again and browse the precise MCP spec [1]. The protocol is JSON-RPC 2.0 [2] over a transport layer. One JSON object per line. Consumer sends, server responds. The spec defines precisely two transports: stdio for native single-client connections, and HTTP with Server-Despatched Occasions for concurrent shoppers.

That’s the entire protocol.

I requested a distinct query: what does this really want that Python’s commonplace library doesn’t already present? sys.stdin, sys.stdout, http.server, threading, queue, pathlib, json. That’s it. Not a single pip set up.

This text is that implementation — each transports, a manufacturing safety mannequin, 50 exams, and the numbers from operating it.

TL;DR

Most MCP implementations really feel heavier than they need to. The spec solely defines two transports, stdio and HTTP/SSE, however in observe they’re often wrapped in frameworks and additional dependencies.

I constructed each transports from scratch utilizing solely the Python commonplace library.

It runs as a single file with one runtime flag. No installs, no setup.

For native work, it makes use of stdio with a single shopper. Once you want concurrency, it switches to HTTP/SSE and handles a number of shoppers with out altering the rest.

Below the hood, every thing stays constant. Similar dispatcher, identical instruments, identical safety mannequin.

As a result of it touches the filesystem, I added strict path checks early on. Frequent escape patterns like ../../, symlink tips, and Home windows UNC paths are blocked.

5 concurrent shoppers. Below 50ms whole wall time. Verified on Home windows 11, Python 3.12.6, CPU solely.

Full code: https://github.com/Emmimal/local-mcp-server/

The Mistake That Formed the Entire Design

Earlier than the structure, I wish to let you know in regards to the factor that just about made me quit on the entire thing.

Early in improvement I used to be testing the search device. I pointed the server at C:UsersAdmin and ran it in search of Python information. The server began. The demo began operating. Then it simply saved operating.

Thirty seconds. A minute. 5 minutes. I believed there was an infinite loop someplace. I went again by means of the code thrice. Every part seemed appropriate. I killed the method and restarted. Similar outcome.

Ten minutes in I lastly understood what was occurring. The search device was utilizing rglob() by default. I had pointed it at my complete consumer listing and it was scanning every thing — digital environments, AppData, each cached file on the machine. Tens of hundreds of information, separately.

I killed the method and altered one line:

# Earlier than — recursive by default, scans every thing
for match in goal.rglob(sample):

# After — shallow by default, opt-in for recursion
for match in goal.glob(sample):

And made recursive=False the default parameter. The shopper has to cross recursive=True explicitly. The server won’t ever scan recursively by itself.

That single change is why search completes in underneath 30ms on an actual challenge folder at this time as a substitute of operating ceaselessly. And it turned the rule I utilized all over the place: no conduct that destroys efficiency ought to ever be the default.

What MCP Truly Is

The Mannequin Context Protocol [1] is a standardised means for AI shoppers to name instruments on exterior servers. It makes use of JSON-RPC 2.0 [2] as its message format.

In observe, this implies AI shoppers like Claude or ChatGPT can immediately entry and motive over native information as a substitute of counting on copy-paste.

The handshake has three phases. First the shopper initializes, then it asks what instruments can be found, then it begins calling them:

Every part after that’s the transport carrying messages backwards and forwards.

The spec defines two transports. stdio runs over commonplace enter and output — one JSON object per line, flushed instantly. HTTP/SSE runs requests over HTTP POST, with responses streamed again over a persistent Server-Despatched Occasions connection [3].

Most implementations choose one. This one implements each, with the identical dispatcher and the identical 4 instruments sitting behind every.

Here’s what the demo exhibits at startup — each transports register the identical instruments:

[2] Accessible instruments
  [list_directory     ] Record information and directories. Returns identify, kind, measurement...
  [read_file          ] Learn a file's contents. Max 1 MB. Binary information returned...
  [search_files       ] Search information by glob sample. Use recursive=true for...
  [get_file_info      ] Get metadata for a file or listing: measurement, kind, ext...

Structure: 4 Layers

The system has 4 layers.

Safety layer — validates each path earlier than any filesystem operation. It runs earlier than the rest, on each single name.

Instruments layer — 4 instruments for the precise file system work: list_directory, read_file, search_files, get_file_info.

Dispatcher — a stateless JSON-RPC router. Parses the tactic, calls the appropriate handler, returns the response. It has no concept which transport is operating and it doesn’t have to.

Transport layer — two implementations. StdioTransport for native AI shoppers. HTTPSSETransport for concurrent connections. The dispatcher has no concept which one is operating.

The entry level selects the transport at startup:

dispatcher = MCPDispatcher(root)

if args.http:
    HTTPSSETransport(dispatcher, host=args.host, port=args.port).run()
else:
    StdioTransport(dispatcher).run()

One flag. That’s it.

The Safety Mannequin

The very first thing I had to consider when constructing a server that reads native information was what stops a shopper from studying information it shouldn’t. The apparent assault is path traversal — as a substitute of sending README.md, a shopper sends ../../and many others/passwd and a server that doesn’t examine follows it straight out of the sandbox.

The repair was to resolve each paths totally earlier than evaluating them. The important thing line:

goal.resolve().relative_to(base.resolve())

Path.resolve() expands all symlinks and collapses all .. segments. relative_to() raises ValueError if the outcome lands exterior the bottom. [6] No string parsing, no counting .. manually. The OS resolves the trail; Python checks the outcome.

MCP_ROOT units the sandbox root by way of atmosphere variable. I set it to my challenge folder particularly, not my dwelling listing. Each device runs this examine earlier than touching the filesystem. If it fails, the error goes again to the shopper instantly.

The safety exams confirm this on each construct:

The 4 Instruments

list_directory

Lists every thing in a listing — identify, kind, measurement, modified timestamp, relative path. Directories earlier than information, hidden entries excluded by default.

Pointing it on the challenge folder:

[3] list_directory
  8 entries:

  [F] concurrent_demo.py                  4,711B
  [F] demo.py                            10,451B
  [F] http_client.py                      5,140B
  [F] local_desktop_config.json             228B
  [F] README.md                           7,542B
  [F] server.py                          29,222B
  [F] test_server.py                     17,500B

Eight entries, sizes, all contained in the sandbox. The kind order places directories first as a result of the type key makes use of p.is_file() — False < True in Python, so directories naturally float up.

One factor that bit me on Home windows: a file can seem in a listing itemizing whereas being locked by one other course of. merchandise.stat() raises PermissionError on that entry. The device wraps every stat name in its personal strive/besides and skips locked entries silently as a substitute of crashing the complete itemizing.

read_file

Reads file contents with a tough 1 MB cap. Textual content information returned as plain UTF-8. Binary information returned as base64.

read_file
  concurrent_demo.py:

  #!/usr/bin/env python3
  """
  concurrent_demo.py
  ============================
  Proves the HTTP/SSE transport handles a number of concurrent shoppers.

  Spins up 5 shoppers concurrently, every operating
  ... (4509 extra chars)

I added the binary fallback after pointing the server at an actual challenge folder for the primary time. Python challenge folders comprise .pyc information, compiled extensions, SQLite databases. The primary model refused all of them with UnicodeDecodeError. The repair: if read_text() fails on decode, fall again to read_bytes() and return base64. The shopper will get a structured response with a binary: true flag as a substitute of a crash.

The 1 MB cap exists as a result of one early take a look at unintentionally learn a 200 MB SQLite database and froze the method for thirty seconds. MAX_FILE_BYTES is a continuing on the high of server.py — change it in case your workflow wants bigger information.

search_files

After the rglob() incident, this device works like this:

[6] search_files — *.py (shallow)
  Discovered 5 file(s):

  -> concurrent_demo.py    4,711B
  -> demo.py              10,451B
  -> http_client.py        5,140B
  -> server.py            29,222B
  -> test_server.py        17,500B

5 information, underneath 30ms. The identical name on C:UsersAdmin with recursive=True would nonetheless scan every thing — however now that could be a deliberate alternative the shopper has to make, not one thing the server does mechanically.

The truncated flag tells the shopper when outcomes had been minimize off at max_results. The primary model silently dropped outcomes with no sign — I added truncated after realising the shopper had no approach to comprehend it wasn’t getting every thing.

get_file_info

Returns metadata with out studying file contents — helpful when the shopper must examine permissions earlier than deciding whether or not to learn.

[4] get_file_info
  identify         local-mcp-server
  path         .
  kind         listing
  measurement         4096
  modified     1780246573
  created      1780227648
  extension    None
  readable     True
  writable     True

os.entry() checks actual permissions, not simply existence. On Home windows a file might be seen in an inventory whereas being locked. Understanding it’s unreadable earlier than attempting to learn it saves a spherical journey.

The Dispatcher

I didn’t wish to reinvent the wheel or rewrite my core logic simply to deal with totally different community setups, so I constructed a central dispatcher to deal with every thing as a substitute. It features as a fundamental, stateless engine. A uncooked JSON string is available in, the dispatcher parses it to see precisely what the shopper wants, after which it drops a response again.

I explicitly saved all community and file I/O out of this element. It doesn’t know something about stdin, stdout, or HTTP. All of that messy communication is left completely to the transport layers. The transports do the heavy lifting with the precise sockets or streams and easily cross the clear knowledge alongside to the dispatch() operate.

To maintain the system lean, the engine solely listens for 4 spec strategies: initialize, instruments/record, instruments/name, and ping. If the rest hits the dispatcher, it shuts the request down instantly with a typical JSON-RPC error.

The one exception is dealing with notifications. When a message comes by means of with out an id area, the MCP specification dictates that no response is required. The dispatcher processes the occasion internally and simply returns None. As a result of the core engine is totally impartial of how knowledge travels, shifting from native stdio to an HTTP server requires zero inner code modifications. The transport layer modifications on the surface, however the primary dispatcher stays precisely the identical.

Transport 1: stdio

For the native setup, the stdio transport is only a uncooked for line in self._stdin loop. I utterly skipped async, threads, and occasion loops to maintain it so simple as doable.

The Home windows repair truly took me longer than writing the transport itself. By default, Python opens stdin and stdout in textual content mode on Home windows, which mechanically modifications each n to rn everytime you write knowledge. That little change utterly corrupts the JSON stream. The second a shopper reads }rn{, it hits a parse error on the very subsequent message, breaking the complete connection.

if platform.system() == "Home windows":
    import msvcrt
    msvcrt.setmode(sys.stdin.fileno(),  os.O_BINARY)
    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)

Setting O_BINARY disables the interpretation. [8] With out this the server works on macOS and Linux and silently breaks on Home windows.

write_through=True on the stdout wrapper ensures each write flushes instantly. The AI shopper is obstructing synchronously ready for the response — any buffering stalls the interplay.

Right here is the complete stdio demo output from my machine:

============================================================
  local-mcp-server demo  [stdio transport]
  Root: C:UsersAdminPycharmProjectspythonProjectlocal-mcp-server
============================================================

[1] Initialize
  Server  : local-mcp-server v1.0.0
  Protocol: 2024-11-05

[2] Accessible instruments
  [list_directory     ] Record information and directories...
  [read_file          ] Learn a file's contents. Max 1 MB...
  [search_files       ] Search information by glob sample...
  [get_file_info      ] Get metadata for a file or listing...

[3] list_directory     8 entries
[4] get_file_info      readable: True  writable: True
[5] read_file          first small file learn efficiently
[6] search_files       Discovered 5 .py information

============================================================
  All checks handed. Prepared to attach Native Desktop.
============================================================

Transport 2: HTTP/SSE

Every shopper opens a GET /sse connection (constructed on Python’s http.server [4]) that stays open for the complete length of the session, permitting the server to push responses down that pipeline as server-sent occasions. Every connection receives a novel client_id [9] on join. When a shopper wants to speak again or ship a request, it fires off a separate POST /message.

The stream per shopper seems like this:

To deal with concurrency cleanly, every shopper will get its personal impartial message queue. [7] The POST handler dispatches the decision, drops the outcome immediately onto that shopper’s queue, and instantly returns a 202 standing. It doesn’t watch for the SSE supply to complete. The shopper simply picks up the response from its personal open stream. That’s what makes the concurrency work.

I arrange 16 daemon employee threads to handle incoming requests. Since every lively SSE connection holds onto one thread, having 5 lively SSE shoppers leaves 11 threads utterly free to deal with incoming POST requests at any second. There isn’t any async/await syntax and no occasion loop—simply commonplace library threading. [5]

The Concurrent Demo

That is the output that solutions whether or not the HTTP/SSE transport truly works:

============================================================
  Concurrent Consumer Demo — 5 shoppers, 5 simultaneous calls
============================================================

  Launching 5 concurrent shoppers...

  Consumer     Device                 Outcome         Time
  ---------- -------------------- ---------- --------
  1          list_directory       OK           ~0.034s
  2          get_file_info        OK           ~0.021s
  3          list_directory       OK           ~0.038s
  4          search_files         OK           ~0.023s
  5          search_files         OK           ~0.021s

Complete wall time: ~0.04s for five concurrent shoppers
Outcome: ALL PASSED
============================================================

5 shoppers. 5 totally different device calls. Below 50ms whole wall time throughout all runs. None blocked one another. Measured on Home windows 11, Python 3.12.6, CPU solely.

What Broke Throughout Improvement

The ten-minute hold I already described. Three different issues broke earlier than the server was steady.

The Home windows rn downside. The primary time I linked an precise AI shopper it obtained a parse error on the second message. Every part seemed fantastic in testing. The problem was the stdout translation — n changing into rn on Home windows. I spent an hour wanting on the dispatcher earlier than I discovered it. Two traces fastened it.

The binary file crash. First model of read_file referred to as read_text() on every thing. First actual challenge folder it hit a .pyc file and raised UnicodeDecodeError. Added the base64 fallback after that.

The 200 MB database freeze. Earlier than the 1 MB cap, a take a look at unintentionally learn a SQLite database. The method froze for thirty seconds. The cap went in instantly after.

Every of those solely appeared when the server ran towards an actual machine, not a take a look at listing.

The Check Suite

50 exams throughout seven courses. Safety runs first.

Run the take a look at suite with pytest in verbose mode. To skip integration exams, cross the not integration marker flag.

Connecting to a Native AI Consumer

macOS: ~/Library/Utility Assist/Claude/local_desktop_config.json

Home windows: %APPDATApercentClaudelocal_desktop_config.json

{
  "mcpServers": {
    "local-desktop": {
      "command": "python",
      "args": ["C:/absolute/path/to/local-mcp-server/server.py"],
      "env": {
        "MCP_ROOT": "C:/absolute/path/to/your/workspace"
      }
    }
  }
}

For HTTP/SSE:

# Terminal 1 — begin the server
python server.py --http --port 8765

# Terminal 2 — run the instance shopper
python examples/http_client.py

Sincere Design Choices

A pool of 16 employee threads is lots for native improvement, however I didn’t design this to scale right into a shared server dealing with a whole bunch of simultaneous connections. If you happen to want that type of scale, it’s best to most likely swap this out for asyncio and a devoted async framework. For native AI tooling operating a handful of shoppers by yourself machine, 16 threads is greater than sufficient.

The safety mannequin trusts the sandbox boundary itself, utterly ignoring file varieties. I didn’t write an allowlist of protected extensions or a blocklist of harmful ones. If a path resolves inside MCP_ROOT, it’s readable. One rule is more durable to get round than ten.

I additionally deliberately neglected token counting. This server merely returns uncooked file contents. Managing your token finances belongs within the execution layer between the server and the mannequin. Including a counter right here would drive a tokenizer dependency—breaking the zero-dependency objective—or drive an approximation with its personal messy edge circumstances.

Lastly, search is shallow by default. A ten-minute hold throughout testing made this choice for me. Any conduct that silently destroys efficiency like that ought to by no means be the default choice.

What This Truly Teaches

I anticipated constructing an MCP server to be difficult. The tutorials made it look difficult. Each implementation I discovered had FastAPI, uvicorn, and three different packages earlier than a single device was registered. So I assumed that complexity was mandatory.

It wasn’t. After I lastly learn the precise spec, the protocol was a loop. Learn a line. Parse JSON. Name a operate. Write a line. That’s it. The frameworks weren’t fixing MCP issues — they had been fixing HTTP issues that MCP over stdio doesn’t have.

The usual library was sufficient as a result of the issue was small. I didn’t want a framework. I wanted http.server for TCP connections, threading for parallel requests, queue to decouple SSE from POST dealing with, and pathlib for path decision. One module per downside. Nothing left over.

The factor that shocked me most was how a lot the defaults mattered. Each actual failure on this codebase — the ten-minute hold, the 200 MB freeze, the Home windows JSON corruption — got here from a default that labored fantastic in testing and broke on an actual machine. rglob() was fantastic on a small take a look at folder. Textual content mode stdout was fantastic on Linux. The default that feels handy in improvement is commonly the one which silently destroys issues in manufacturing.

Full code: https://github.com/Emmimal/local-mcp-server/

References

[1] Mannequin Context Protocol. (n.d.). Mannequin Context Protocol Specification. https://modelcontextprotocol.io

[2] JSON-RPC Working Group. (2010). JSON-RPC 2.0 Specification. https://www.jsonrpc.org/specification

[3] WHATWG. (n.d.). Server-sent occasions. HTML Dwelling Customary. https://html.spec.whatwg.org/multipage/server-sent-events.html

[4] Python Software program Basis. http.server — HTTP servers. Python 3 Documentation. https://docs.python.org/3/library/http.server.html

[5] Python Software program Basis. threading — Thread-based parallelism. Python 3 Documentation. https://docs.python.org/3/library/threading.html

[6] Python Software program Basis. pathlib — Object-oriented filesystem paths. Python 3 Documentation. https://docs.python.org/3/library/pathlib.html

[7] Python Software program Basis. queue — A synchronized queue class. Python 3 Documentation. https://docs.python.org/3/library/queue.html

[8] Python Software program Basis. msvcrt — Helpful routines from the MS VC++ runtime. Python 3 Documentation. https://docs.python.org/3/library/msvcrt.html

[9] Python Software program Basis. (n.d.). uuid — UUID objects in keeping with RFC 4122. Python 3 Documentation. https://docs.python.org/3/library/uuid.html

[10] Python Software program Basis. subprocess — Subprocess administration. Python 3 Documentation. https://docs.python.org/3/library/subprocess.html

Disclosure

All code on this article was written by me and is authentic work, developed and examined on Python 3.12.6, Home windows 11, CPU solely. No GPU was used at any stage. All benchmark numbers — response instances, concurrent shopper outcomes, take a look at counts — are from precise runs on my native machine and are totally reproducible by cloning the repository and operating demo.py and concurrent_demo.py as described above. Your complete implementation makes use of solely the Python commonplace library. No third-party packages are required or used at any level. All structure choices, implementation selections, design tradeoffs, debugging experiences, and the failures described in “What Broke Throughout Improvement” are my very own. I’ve no monetary relationship with any device, library, framework, or firm talked about on this article. The MCP protocol is an open specification printed by Anthropic [1]; this implementation is impartial and isn’t affiliated with or endorsed by Anthropic.

If you happen to construct manufacturing AI techniques and wish to go deeper — tutorials, studying tracks, and hands-on tasks at EmiTechLogic, my AI and Python studying platform.