# forthling (mcpb · forthling.mcpb)

Run Forth-2012 in a sandbox: definitions stay between calls, each result shows the stacks.

- Trust score: 39/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `forthling.mcpb`: 39/100 (this document), [markdown](https://verifymcp.io/servers/deschaker-forthling/forthling.md), [page](https://verifymcp.io/servers/deschaker-forthling/forthling)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/DeSchaker/forthling/releases/download/v0.2.2/forthling.mcpb`
- Transport: `stdio`
- SHA-256: `be6c2a6c830023814538231a02a5eca7b91dcbe7ea3c5af778d372939830a6f9`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1236 tokens (~309/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the forthling MCP server?

forthling ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, be6c2a6c830023814538231a02a5eca7b91dcbe7ea3c5af778d372939830a6f9; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/DeSchaker/forthling/releases/download/v0.2.2/forthling.mcpb`
- SHA-256: `be6c2a6c830023814538231a02a5eca7b91dcbe7ea3c5af778d372939830a6f9`

### Verify on macOS / Linux

```bash
echo "be6c2a6c830023814538231a02a5eca7b91dcbe7ea3c5af778d372939830a6f9  forthling.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\forthling.mcpb).Hash -eq "be6c2a6c830023814538231a02a5eca7b91dcbe7ea3c5af778d372939830a6f9"
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 39, −1)

- [functional regression] Security disclosure: pass → unverified

### 2026-11-04 (score 40, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 39, +1)

- [security regression] Stability: 0.00 → unverified
- [functional regression] Schema quality: 270 → 309

### 2026-11-01 (score 38)

First indexed and scored.

## MCP tools (4)

### `forth_eval` (~268 tokens)

Run Forth

Runs Forth-2012 code in the session and returns what it printed, the data stack and the float stack, and the error if there was one. Definitions, variables, files and the stacks stay for the next call. Large input goes in data, which the code reads with DATA; source files to INCLUDE go in files.

Input parameters:

- `code` (string, required): Forth source; it may have several lines, each at most 1024 characters
- `data` (string): Text for the word DATA ( -- c-addr u ), which gives a copy in ALLOCATEd memory (FREE it); without a line limit, for large input such as JSON. It stays for later calls until another call sends data.
- `files` (object): Files to put in the session's file system before the code runs, as {"name": "text"}, replacing files of the same name; the code can INCLUDE them or open them with the FILE words. The files are in mem…
- `trace` (boolean): If true, the result also gives a trace: each word that ran (not inside the built-in words), with how deep it was nested and the data stack when it started; at most 1000 words. For finding where code…

Output parameters:

- `breaks` (array): forth_eval only, when BREAK ran: what the program looked like at each BREAK (ALSO DEBUG), at most 100; BREAK does not stop the program
- `breaks_dropped` (integer): the BREAKs past the first 100
- `compiling` (boolean): whether a colon definition is still open
- `error` (object|null)
- `fstack` (array): the float stack, the top last
- `max_depth` (integer): forth_eval only: the deepest the data stack was during this call
- `output` (string): what the code printed
- `stack` (array): the data stack, the top last
- `steps` (integer): forth_eval only: the steps this call took, of its limit
- `trace` (array): forth_eval with trace only: a word per entry, in the order they ran
- `trace_dropped` (integer): forth_eval with trace only: the words past the first 1000, which the trace leaves out

### `forth_stack` (~21 tokens)

Show the stacks

Shows the data stack and the float stack, without running anything.

Output parameters:

- `breaks` (array): forth_eval only, when BREAK ran: what the program looked like at each BREAK (ALSO DEBUG), at most 100; BREAK does not stop the program
- `breaks_dropped` (integer): the BREAKs past the first 100
- `compiling` (boolean): whether a colon definition is still open
- `error` (object|null)
- `fstack` (array): the float stack, the top last
- `max_depth` (integer): forth_eval only: the deepest the data stack was during this call
- `output` (string): what the code printed
- `stack` (array): the data stack, the top last
- `steps` (integer): forth_eval only: the steps this call took, of its limit
- `trace` (array): forth_eval with trace only: a word per entry, in the order they ran
- `trace_dropped` (integer): forth_eval with trace only: the words past the first 1000, which the trace leaves out

### `forth_words` (~26 tokens)

List my words

Lists the words defined in this session, the latest first (not the built-in words).

Output parameters:

- `words` (array)

### `forth_reset` (~34 tokens)

Start over

Starts a new Forth session: every definition, variable and stack value is gone, and so are the data and the files.

Output parameters:

- `breaks` (array): forth_eval only, when BREAK ran: what the program looked like at each BREAK (ALSO DEBUG), at most 100; BREAK does not stop the program
- `breaks_dropped` (integer): the BREAKs past the first 100
- `compiling` (boolean): whether a colon definition is still open
- `error` (object|null)
- `fstack` (array): the float stack, the top last
- `max_depth` (integer): forth_eval only: the deepest the data stack was during this call
- `output` (string): what the code printed
- `stack` (array): the data stack, the top last
- `steps` (integer): forth_eval only: the steps this call took, of its limit
- `trace` (array): forth_eval with trace only: a word per entry, in the order they ran
- `trace_dropped` (integer): forth_eval with trace only: the words past the first 1000, which the trace leaves out

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/deschaker-forthling/forthling#diagnostics

## Score history

- 2026-11-05: 39
- 2026-11-04: 40
- 2026-11-03: 39
- 2026-11-02: 39
- 2026-11-01: 38

## Common questions

### What is the forthling MCP server?

forthling is an MCP server listed in the public MCP registry as io.github.DeSchaker/forthling. Run Forth-2012 in a sandbox: definitions stay between calls, each result shows the stacks. This page covers its MCPB bundle (https://github.com/DeSchaker/forthling/releases/download/v0.2.2/forthling.mcpb).

### Is the forthling MCP server safe to use?

forthling scores 39 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the forthling MCP server expose?

forthling exposes 4 tools: forth_eval, forth_stack, forth_words, forth_reset. Their descriptions and schemas cost roughly 349 tokens of context every time the server is loaded.

### What licence is the forthling MCP server under?

forthling declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the forthling MCP server?

VerifyMCP ran 11 checks on forthling, covering Source repository, Provenance, License, Maintenance and 7 more. 5 items could not be completed, a gap on our side rather than a finding about forthling: Malware scan, Known CVEs, Install scripts, Dependency health and 1 more. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Repository: https://github.com/DeSchaker/forthling
- Website: https://deschaker.github.io/forthling/
- Changelog RSS feed: https://verifymcp.io/servers/deschaker-forthling/forthling.xml
- Changelog JSON feed: https://verifymcp.io/servers/deschaker-forthling/forthling/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/deschaker-forthling/forthling.json
- HTML version of this page: https://verifymcp.io/servers/deschaker-forthling/forthling