About forthling
forthling is an MCP server for running Forth code in a sandbox, for AI agents and other MCP clients. It preserves definitions and stacks between calls and returns text plus structured results, including errors, traces and stack data.
Key features
- 01Evaluate Forth in a persistent session
- 02Inspect data and float stacks
- 03List session words and look up help
- 04Load and retain in-memory files
- 05Return structured errors, traces and tests
- 06Apply per-call time and resource limits
Use cases
- 01Run and inspect Forth snippets from an agent
- 02Reuse Forth definitions across calls
- 03Diagnose stack errors with traces and source locations
MCP support
Exposes Forth evaluation and session-inspection tools to MCP clients over stdio. Each client session runs in the sandbox, with optional HTTP access restricted to explicitly allowed hosts.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEforthling-mcp
An MCP server that lets AI agents (Claude Code, Claude Desktop and other MCP clients) run Forth in forthling, always in its sandbox. The agent keeps one session: the words it defines and the stacks stay between calls.
Installing
Without Rust, as an MCP bundle: download forthling.mcpb from the
latest release and open it in
Claude Desktop (or another client that installs .mcpb files). The bundle holds the
server for Windows (x64), macOS (Apple Silicon and Intel) and Linux (x64).
From crates.io, with Rust 1.85 or newer:
cargo install forthling-mcp
It builds SQLite along, which takes a C compiler (on Windows that of Visual Studio, which
Rust there uses anyway); cargo install forthling-mcp --no-default-features leaves SQLite
out. From a clone of the repository: cargo install --path mcp, or
cargo build --release --manifest-path mcp/Cargo.toml, and the program is then
mcp/target/release/forthling-mcp. With Claude Code:
claude mcp add forthling -- forthling-mcp
Other clients start it the same way: the command forthling-mcp, over stdio.
When a client connects, the server tells the model the basics in its instructions: the
idioms that trip models up, locals rather than ROT, PICK and ROLL, the JSON words and
the limits. llms.txt says the same at more length, for a model that reads
it beforehand; a test keeps the limits in both the same.
Tools
| Tool | Arguments | |
|---|---|---|
forth_eval | code, data, files, trace | runs Forth code; returns the output, the data and float stacks, and the error if there was one |
forth_stack | the stacks, without running anything | |
forth_words | the words defined in this session, the latest first | |
forth_help | word | the stack effect of a word, what it does, an example, and the word list it is in; for a name that is not defined, close names. Words of the session show the ( ) comment after their name |
forth_reset | a new session: every definition, stack value, the data and the files are gone |
A line of code, and so a string in S", is at most 1024 characters. Larger input, such
as a JSON document, goes in data: the code reads it with DATA ( -- c-addr u ), which
gives a copy in ALLOCATEd memory (FREE it). The data stays for later calls until a
call sends other data, and may be at most as large as the Forth memory:
{"name": "forth_eval", "arguments": {"code": "ALSO JSON DATA JSON-LENGTH .", "data": "[[59],[73,41]]"}}
Each session has files of its own, in memory and never on the disk: INCLUDE, REQUIRE,
the FILE words and the block words use them, and they stay until forth_reset. files
puts files there before the code runs, as an object of names and texts, replacing files of
the same name; so an agent can give a library once and INCLUDE it, and what the code
writes, a later call can read. The files take at most 4 MiB in all; a write past that
fails with the word's ior, and files that do not fit are refused.
{"name": "forth_eval", "arguments": {"code": "INCLUDE square.fs 7 SQUARE .", "files": {"square.fs": ": SQUARE DUP * ;"}}}
Each result is text the way the REPL shows it:
2401 ok
stack: 1 2
and the same as structured JSON (structuredContent, with an outputSchema):
{"output": "2401 ", "stack": [1, 2], "fstack": [], "compiling": false, "error": null, "steps": …, "max_depth": …}; steps and max_depth (only for forth_eval) tell how
many steps the call took and how deep the data stack went, counting the words of the
system it ran (. is written in Forth, so it counts too).
An error empties the stacks, so the result also tells what they held at the error, where it happened and which words were running; the model can put it right in one go:
error -10: division by zero
at input, line 2, column 3: MAIN
in: MAIN > STEP > /
stack at the error: 5 1
stack: empty
and as JSON: "error": {"code": -10, "message": "division by zero", "stack": [5, 1], "fstack": [], "words": ["MAIN", "STEP", "/"], "source": "input", "line": 2, "column": 3, "token": "MAIN", …}, with isError true. A word that took its arguments before it
failed, such as / here, has taken them. An undefined word that is in a word list
outside the search order gets a hint, which the text adds after the word:
error -13: undefined word: JSON@ (it is in the word list JSON; ALSO JSON finds it).
A runaway program can leave a hundred thousand cells on the stack, or as many words
running (endless recursion). The result then keeps the top 32 cells and the innermost 32
words, the text says ... (n more) and the JSON has the full depth in stack_depth,
fstack_depth and words_depth. A definition that is still open (compiling true)
says so in the text: compiled (a definition is still open; ; ends it).
When the code ran T{ ... -> ... }T tests (ALSO TESTING), the result also has the counts
of that call, and the text starts with tests: 1 passed, 1 failed. The failure lines
(FAIL input:3 (sums): incorrect result: expected <1> 3, got <1> 2) are in the output.
In JSON: "tests": {"passed": 1, "failed": 1, "failures": [{"source": "input", "line": 3, "group": "sums", "expected": [3], "expected_depth": 1, "actual": [2], "actual_depth": 1, "stack": [], "expected_floats": [], "expected_floats_depth": 0, "actual_floats": [], "actual_floats_depth": 0}], "failures_dropped": 0}. The first 32 failures are kept, and each
list keeps its top 32 cells and floats (the depths tell how many there were). A file given with files
shows its name as source.
What an agent sees for typical mistakes
Each case was run through forth_eval (#47); the answer is the first lines of the text.
The code was run from a fresh session.
| Mistake | Code | Answer |
|---|---|---|
| undefined word | 1 2 FOO . | error -13: undefined word: FOO, the column, the stack at the error 1 2 |
| word in a word list not in the search order | S" :memory:" DB-OPEN | error -13: undefined word: DB-OPEN (it is in the word list SQLITE; ALSO SQLITE finds it) |
| undefined word in a definition | : sq DUPP * ; | error -13: undefined word: DUPP, at its column |
| stack underflow | : add2 + ; 1 add2 | error -4: stack underflow, in: ADD2 > +, the stack at the error |
| word that eats too much | : f ( n -- ) DROP ; f | error -4, in: F > DROP |
IF, DO, BEGIN outside a definition | 1 IF 2 THEN | error -14: interpreting a compile-only word: IF |
unclosed IF | : foo 1 IF 2 ; | error -22: control structure mismatch, at the ; |
LOOP without DO | : f LOOP ; | error -22: control structure mismatch |
| unclosed definition | : foo 1 2 + | compiled (a definition is still open; ; ends it) |
| division by zero | 1 0 / | error -10: division by zero, in: /, stack at the error empty (/ took its arguments) |
| bad address | 12345678 @ | error -9: invalid memory address: 12345678 |
| step limit | : spin BEGIN 1 DROP AGAIN ; spin | error -258: limit exceeded: steps, in: SPIN > DROP |
| output limit | : p BEGIN 65 EMIT AGAIN ; p | the output up to the limit, then error -258: limit exceeded: output |
| endless stack growth | : grow BEGIN 1 AGAIN ; grow | error -3: stack overflow, the top 32 cells and ... (n more) |
| endless recursion | : r RECURSE ; r | error -5: return stack overflow, the innermost 32 words |
| missing file | S" nofile.fth" INCLUDED | error -38: non-existent file: nofile.fth: no such file |
error inside EVALUATE | S" 1 2 FOO" EVALUATE | at evaluate, line 1, column 5: FOO, stack 1 2 |
| line over 1024 characters | S" xxxx…" TYPE | error -18: parsed string overflow: input line too long |
ABORT" | : chk 0= ABORT" zero" ; 0 chk | error -2: aborted: zero |
CATCH | : t 1 0 / ; : u ['] t CATCH . ; u | prints -10, no error result |
What gives no error, and so no message: an unclosed S" or ( takes the rest of the
line (as the standard says); : f >R ; leaves the return stack unbalanced and 1 f
returns without a word; ALLOCATE of a negative size and FREE twice answer with a
non-zero ior on the stack (-59, -60), and so does a failed DB-EXEC (-261); a
JSON path that is not there gives 0 0 0. These follow the standard or the word's
stack effect; the agent must read the stack.
With "trace": true, forth_eval also returns a trace: each word that ran, with how deep
it was nested and the data stack when it started (at most its top 8 cells), at most 1000
words; trace_dropped counts the rest. The insides of the system's own words are left
out. The text starts with it, indented the way TRACE-ON prints it:
trace:
F <0>
SQ <1> 3
DUP <1> 3
* <2> 3 3
1+ <1> 9
. <1> 10
end of trace
10 ok
stack: empty
and the JSON has "trace": [{"word": "F", "depth": 0, "stack": [], "stack_depth": 0}, {"word": "SQ", "depth": 1, "stack": [3], "stack_depth": 1}, …], "trace_dropped": 0. The
trace of a call that fails shows how it got to the error. In the code itself,
ALSO DEBUG TRACE-ON … TRACE-OFF prints the same lines as output.
BREAK (also ALSO DEBUG) marks a place to look at. It does not stop the program, since
no one could answer in the middle of a call; instead the result has breaks, what the
program looked like at each BREAK (at most 100; breaks_dropped counts the rest), with
the same fields as an error: stack, fstack, words, source, line, column and
token. The text starts with a line for each:
break 1: in F > BREAK, at input, line 1, column 3: stack <2> 7 9
ALSO TUTORIAL gives the tutorial: 20 lessons of Forth, ten for beginners and ten
beyond, that an agent can walk a person through (LESSONS, n LESSON, CHECK tests the
answer, HINT, NEXT).
The JSON words are installed (ALSO JSON), and the SQLite words for databases in memory
(ALSO SQLITE, only :memory:, which SQL stops when the time is up and which cannot
grow larger than the Forth memory) and the regular expression words (ALSO REGEX, which
match in linear time) and the vector, matrix, linear algebra and special function words (ALSO SCIENCE); without the Cargo features sqlite, regex and science
(--no-default-features) the server is built without them.
The HTTP words (ALSO HTTP, see http/README.md) are a third feature,
http, which is off by default because it reaches the network. Build the server with it
(cargo install forthling-mcp --features http) and start it with the hosts that Forth code
may send requests to, once for each host: forthling-mcp --allow-host api.example.com
(*.example.com and * also work). Without --allow-host the network stays closed and the
model is not told about the words. It is the only option that opens something outside the
sandbox, and only for the hosts you name; a Forth word cannot add one.
The sandbox
Every session runs in forthling's sandbox: files only in memory, and each call at most 10 million steps, 5 seconds and 1 MiB of output; the session's definitions and the like at most 4 MiB in all. The options change these limits, each up to a ceiling the program fixes:
-m, --memory SIZE Forth memory (default 1M) [64M]
--max-steps N steps per call (default 10000000) [1000000000]
--max-time T time per call, such as 5s or 500ms (default 5s) [60s]
--max-output SIZE output per call (default 1M) [16M]
--max-space SIZE definitions and the like in all (default 4M) [64M]
--allow-host HOST a host that Forth code may send HTTP requests to (repeat)
There is no option to switch the sandbox off or to permit files, so changing how the
server is started does not open them either. Only --allow-host opens the network, for
the hosts it names (see above).
What enforces it. The sandbox is enforced by the server, not by what the model is
told or promises: the tools take only Forth code (other arguments are refused), and no
Forth word can change a limit or a permission. A user who asks the AI to get around the
sandbox cannot do it through forthling. An agent that also has other tools, such as a
shell or editing files, can however go around it: change the MCP configuration, or start
another program. Against that, forthling cannot help; use the permissions of the agent
instead. In Claude Code: deny or limit the shell, deny edits to the MCP configuration
(.mcp.json, ~/.claude.json), and allow only the MCP servers you want through managed
settings. For extra safety against a bug in forthling, run the server in a container or
as a user with few rights.
Testing
cargo test --manifest-path mcp/Cargo.toml
cargo test --manifest-path mcp/Cargo.toml --no-default-features
cargo test --manifest-path mcp/Cargo.toml --all-features
Links
- Source and the rest of forthling: https://github.com/DeSchaker/forthling
- The MCP Registry knows this server as
io.github.DeSchaker/forthling(the line below lets it check that the crate is ours). - mcp-name: io.github.DeSchaker/forthling
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.