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

. The features had grown too lengthy and the variable names made no sense anymore. Each time I wished 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 plain repair was to provide the AI instrument direct entry to my challenge folder. That’s after I bumped into MCP — the Mannequin Context Protocol — which is strictly constructed for this. A server runs regionally, exposes instruments, and the AI consumer 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 and not using a combat.

I stepped again and skim 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 unique query: what does this really need that Python’s normal 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 assessments, 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 apply they’re normally wrapped in frameworks and additional dependencies.

I constructed each transports from scratch utilizing solely the Python normal 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 consumer. Whenever you want concurrency, it switches to HTTP/SSE and handles a number of shoppers with out altering anything.

Underneath the hood, every part stays constant. Identical dispatcher, similar instruments, similar 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. Underneath 50ms complete 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 almost made me surrender on the entire thing.

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

Thirty seconds. A minute. 5 minutes. I assumed there was an infinite loop someplace. I went again by way of the code 3 times. Every little thing regarded appropriate. I killed the method and restarted. Identical consequence.

Ten minutes in I lastly understood what was taking place. The search instrument was utilizing rglob() by default. I had pointed it at my complete consumer listing and it was scanning every part — digital environments, AppData, each cached file on the machine. Tens of 1000’s of information, one by one.

I killed the method and adjusted one line:

# Earlier than — recursive by default, scans every part
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 consumer has to move recursive=True explicitly. The server won’t ever scan recursively by itself.

That single change is why search completes in below 30ms on an actual challenge folder at the moment as a substitute of operating ceaselessly. And it grew to become the rule I utilized in all places: no conduct that destroys efficiency ought to ever be the default.

What MCP Truly Is

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

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

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

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

The spec defines two transports. stdio runs over normal 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 decide one. This one implements each, with the identical dispatcher and the identical 4 instruments sitting behind every.

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

[2] Out there instruments
  [list_directory     ] Record information and directories. Returns identify, sort, 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, sort, ext...

Structure: 4 Layers

The system has 4 layers.

Safety layer — validates each path earlier than any filesystem operation. It runs earlier than anything, 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 strategy, calls the correct 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 consumer from studying information it shouldn’t. The plain assault is path traversal — as a substitute of sending README.md, a consumer sends ../../and so forth/passwd and a server that doesn’t verify 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 consequence lands exterior the bottom. [6] No string parsing, no counting .. manually. The OS resolves the trail; Python checks the consequence.

MCP_ROOT units the sandbox root by way of surroundings variable. I set it to my challenge folder particularly, not my residence listing. Each instrument runs this verify earlier than touching the filesystem. If it fails, the error goes again to the consumer instantly.

The safety assessments confirm this on each construct:

The 4 Instruments

list_directory

Lists every part in a listing — identify, sort, 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 type 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 instrument wraps every stat name in its personal attempt/besides and skips locked entries silently as a substitute of crashing all the 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 consumer 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 check by chance 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 instrument 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, below 30ms. The identical name on C:UsersAdmin with recursive=True would nonetheless scan every part — however now that may be a deliberate alternative the consumer has to make, not one thing the server does robotically.

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

get_file_info

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

[4] get_file_info
  identify         local-mcp-server
  path         .
  sort         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 could be seen in a list 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 part 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 consumer 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 solely to the transport layers. The transports do the heavy lifting with the precise sockets or streams and easily move the clear knowledge alongside to the dispatch() perform.

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

The one exception is dealing with notifications. When a message comes by way of with out an id subject, 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 unbiased of how knowledge travels, shifting from native stdio to an HTTP server requires zero inner code adjustments. The transport layer adjustments on the skin, 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 fully skipped async, threads, and occasion loops to maintain it so simple as doable.

The Home windows repair really took me longer than writing the transport itself. By default, Python opens stdin and stdout in textual content mode on Home windows, which robotically adjustments each n to rn everytime you write knowledge. That little change fully corrupts the JSON stream. The second a consumer reads }rn{, it hits a parse error on the very subsequent message, breaking all the 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 consumer is obstructing synchronously ready for the response — any buffering stalls the interplay.

Right here is the total 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] Out there 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 consumer opens a GET /sse connection (constructed on Python’s http.server [4]) that stays open for all the 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 consumer wants to speak again or ship a request, it fires off a separate POST /message.

The stream per consumer seems to be like this:

To deal with concurrency cleanly, every consumer will get its personal unbiased message queue. [7] The POST handler dispatches the decision, drops the consequence immediately onto that consumer’s queue, and instantly returns a 202 standing. It doesn’t look forward to the SSE supply to complete. The consumer 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 energetic SSE connection holds onto one thread, having 5 energetic SSE shoppers leaves 11 threads fully free to deal with incoming POST requests at any second. There is no such thing as a async/await syntax and no occasion loop—simply normal library threading. [5]

The Concurrent Demo

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

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

  Launching 5 concurrent shoppers...

  Consumer     Software                 End result         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
End result: ALL PASSED
============================================================

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

What Broke Throughout Growth

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

The Home windows rn drawback. The primary time I related an precise AI consumer it obtained a parse error on the second message. Every little thing regarded fantastic in testing. The difficulty was the stdout translation — n changing into rn on Home windows. I spent an hour trying on the dispatcher earlier than I discovered it. Two strains mounted it.

The binary file crash. First model of read_file referred to as read_text() on every part. 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 check by chance 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 check listing.

The Take a look at Suite

50 assessments throughout seven lessons. Safety runs first.

Run the check suite with pytest in verbose mode. To skip integration assessments, move the not integration marker flag.

Connecting to a Native AI Consumer

macOS: ~/Library/Utility Help/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 consumer
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 tons of of simultaneous connections. Should you want that form of scale, you need to in all probability 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, fully ignoring file sorts. I didn’t write an allowlist of secure extensions or a blocklist of harmful ones. If a path resolves inside MCP_ROOT, it’s readable. One rule is tougher to get round than ten.

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

Lastly, search is shallow by default. A ten-minute cling 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 instrument was registered. So I assumed that complexity was mandatory.

It wasn’t. Once I lastly learn the precise spec, the protocol was a loop. Learn a line. Parse JSON. Name a perform. 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 drawback. Nothing left over.

The factor that stunned me most was how a lot the defaults mattered. Each actual failure on this codebase — the ten-minute cling, 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 check folder. Textual content mode stdout was fantastic on Linux. The default that feels handy in improvement is usually 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 Residing Normal. 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 line 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 consumer outcomes, check 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. The whole implementation makes use of solely the Python normal library. No third-party packages are required or used at any level. All structure selections, implementation selections, design tradeoffs, debugging experiences, and the failures described in “What Broke Throughout Growth” are my very own. I’ve no monetary relationship with any instrument, library, framework, or firm talked about on this article. The MCP protocol is an open specification revealed by Anthropic [1]; this implementation is unbiased and isn’t affiliated with or endorsed by Anthropic.

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