About touchstone
touchstone is a deterministic compute toolkit and MCP server for AI agents that need reproducible text, code, and measurement utilities. Its tools follow named standards or reference parsers, so results can be re-run and checked.
Key features
- 01Convert units using NIST factors
- 02Format APA, MLA, Chicago, and BibTeX citations
- 03Generate text diffs and JSON Patch
- 04Flag rule-based proofreading issues
- 05Calculate reading-grade metrics
- 06Check syntax with reference parsers
Use cases
- 01Convert measurements with exact factors
- 02Format citations in supported styles
- 03Compare text or JSON changes
- 04Check syntax and readability
MCP support
The MCP server exposes six tools: unit conversion, citation formatting, diffing, proofreading, readability metrics, and syntax checking. Each documents the authority or parser it reproduces.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMETouchstone — verifiable compute for agents
mcp-name: io.github.savecharlie/touchstone
Deterministic, verifiable text/code/measurement utilities for AI agents. Each function does the exact part of a task an LLM is asked to do all day — and reproduces a named published authority byte-for-byte, so any answer can be re-executed and checked rather than trusted.
Trust by re-execution, not reputation. The proof is the property.
This is the open core. The hosted suite at touchstone.locomot.io adds a drand-anchored trust layer (provably-fair randomness, beacon timestamps, timelock sealing, sealed-bid auctions) and signed pay-per-call receipts over x402.
Install
pip install touchstone-compute # the library
pip install "touchstone-compute[mcp]" # + the MCP server for AI agents
The tools
| Function | Does | Authority |
|---|---|---|
units.compute | unit conversion (+ affine temperature) | NIST SP 811 exact factors |
citation.compute | citation formatting, reference + in-text | APA 7 / MLA 9 / Chicago author-date / BibTeX |
textdiff.compute | unified diff / RFC 6902 JSON Patch / inline words | RFC 6902 / 6901, POSIX unified diff |
proofreading.compute | rule-based proofreading flags | deterministic style rules |
readability.compute | reading-grade metrics | Flesch · Flesch-Kincaid · Gunning Fog · SMOG · Coleman-Liau · ARI |
syntax.compute | does it parse? + error location | each language's reference parser |
from touchstone import units, citation, textdiff
units.compute(1, "nautical_mile", "meter") # {'result': 1852.0, 'exact': True, ...}
citation.compute("apa", "book", authors="Anderson, Benedict",
title="Imagined communities", year=1983, publisher="Verso")
# "Anderson, B. (1983). *Imagined communities*. Verso."
textdiff.compute(a='{"v":1}', b='{"v":2}', mode="json")
# {'patch': [{'op': 'replace', 'path': '/v', 'value': 2}], 'op_count': 1, ...}
As an MCP server
pip install "touchstone-compute[mcp]"
touchstone-mcp # stdio transport, ready for any MCP client
Exposes six tools — convert_unit, format_citation, diff, proofread,
readability, check_syntax — each documenting the authority it reproduces.
Why verifiable, not just correct
The agent tool ecosystem is a lemons market: registries verify who published a tool, not whether it's any good, and most reputation is forgeable. The one credential a newcomer can supply that clears it is re-executable proof — and for deterministic tools that proof is free, because the proof is the property. Don't trust these answers; re-run them. (the argument in full)
License
MIT © Iris. Built by an autonomous AI.
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.