1. Conduid
  2. Search
  3. Wheat
MCP server · Search

Wheat

Structured research sprints for AI coding agents. Claims, conflicts, compilation.

39Low

Scored 4 months ago · breakdown

About Wheat

Wheat is an MCP server in the Search category: structured research sprints for AI coding agents. Claims, conflicts, compilation. It has been installed 0 times through Conduid.

Install

Clone
git clone https://github.com/grainulation/wheat

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Wheat

Powered by Claude · Grounded in docs

I know everything about Wheat. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • ·Scoped permissionsNot checked yet.

README

The problem

You're about to mass-migrate 200 microservices. The decision is based on a Slack thread, a blog post, and a gut feeling from someone who left the company.

Claude contradicts itself over long sessions. Decisions accumulate silently conflicting evidence. And nobody notices until the migration is six months in and the original assumptions were wrong.

You'd never ship code without tests. Why ship a decision without validated evidence?

What wheat does

Wheat is a CLI that turns your AI coding tool into a structured research engine. Every finding becomes a typed, evidence-graded claim. A 7-pass compiler catches contradictions, flags weak evidence, and blocks output until issues are resolved.

You investigate  →  Claims accumulate  →  Compiler validates  →  Brief compiles
  /research          typed + graded        catches conflicts      backed by evidence
  /prototype         with evidence tiers   blocks on issues
  /challenge

The result: a decision document backed by validated evidence, not vibes.

Quick start

npx @grainulation/wheat "Should we migrate from microservices back to a modular monolith?"

One command. Zero config. Sprint ready in under 3 seconds.

Then open your AI coding tool and start investigating:

wheat add --id r001 --type factual --topic "service-consolidation-latency" \
  --content "Network calls between services become in-process calls when consolidated — p99 drops 40-60%" \
  --evidence documented

wheat search --topic "consolidation"

wheat compile   # 7-pass validation: conflicts, weak evidence, coverage gaps

wheat resolve   # fix what the compiler flags

Works with Claude Code, Cursor, GitHub Copilot, or standalone via CLI.

See it in 30 seconds

npx @grainulation/wheat quickstart

Creates a demo sprint with pre-seeded claims, an intentional conflict, compiles everything, and opens a dashboard. The compiler flags the conflict and blocks output until it's resolved.

What you get

After a sprint, wheat compile produces a compilation.json with:

  • Conflict detection -- contradictory claims are surfaced and must be resolved
  • Evidence coverage -- which topics have only "someone said so" vs. tested proof
  • Type diversity -- flags when every claim is the same type (all risks, no facts)
  • Echo chamber warnings -- same source corroborating itself

The compiler is the enforcement layer. If it says blocked, no brief gets produced. Same principle as CI: red build = no deploy.

MCP integration (optional)

For native tool access in Claude Code:

claude mcp add wheat -- npx -y -p @grainulation/wheat wheat-mcp

This gives Claude direct access to wheat's claims engine -- add-claim, compile, search, status -- without shelling out.

Commands

Command What it does
/research <topic> Deep dive, creates evidence-graded claims
/prototype Build something testable, upgrade evidence to tested
/challenge <id> Adversarial stress-test of a claim
/witness <id> <url> External corroboration from primary sources
/blind-spot Find gaps in your investigation
/resolve Adjudicate conflicts between claims
/brief Compile the decision document
/status Sprint dashboard

Claim types and evidence tiers

Types: constraint, factual, estimate, risk, recommendation, feedback

Evidence tiers (lowest to highest): stated → web → documented → tested → production

The compiler uses these to score coverage. A topic with 5 stated claims is weaker than one with 2 tested claims.

Guard rails

Wheat installs two optional guard mechanisms:

  1. Git pre-commit hook -- prevents committing broken claims
  2. Claude Code guard hook -- prevents generating output from stale compilations

Requirements

Node 20+. Zero third-party runtime dependencies — depends only on @grainulation/barn (internal ecosystem utilities).

Wheat doesn't care what language your project uses. Your Scala project, your Python monorepo, your Flutter app -- wheat validates decisions, not code.

Part of the grainulation ecosystem

Start with wheat. That's the only tool you need.

If you grow into multi-sprint coordination, the ecosystem has you covered: orchard for orchestration, farmer for permission management, and more at grainulation.com.

Removing Wheat

# Remove sprint files
rm -f claims.json compilation.json CLAUDE.md.bak

# Remove wheat section from CLAUDE.md (or delete if wheat created it)
rm -f CLAUDE.md

# Remove slash commands and MCP config
rm -rf .claude/commands/wheat/
rm -f .mcp.json   # or remove just the "wheat" entry

# Remove pre-commit hook snippet (or delete .git/hooks/pre-commit)

Releases

See CHANGELOG.md for release history.

License

MIT

README mirrored from the source repository 4 months ago. The original is authoritative.

Questions

About Wheat

How do I install Wheat?

Run git clone https://github.com/grainulation/wheat, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Wheat safe to use with an AI agent?

Its trust score is 39 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Wheat still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.