adrkit decision memory MCP server
Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.
16 stars419 downloads/wk
Reviews
Write oneNobody has reviewed adrkit decision memory yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
adrkit decision memory tools (4)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
get_decisionFetch one architecture decision by its bare local id (e.g. "0042"). Returns the complete typed frontmatter and Markdown body, or an explicit not-found / ambiguous-local-id / federated-log-unavailable outcome. Relation refs are surfaced verbatim, never expanded.
get_decision_contextGiven repo-relative logical file paths, report which decisions govern them, which active proposals touch them, and which historical records once did — using the corpus’s own affects matchers. The supplied paths are compared against patterns only; they are never opened or read.
list_supersededList every superseded decision with its direct local replacement state: resolved, dangling, ambiguous (candidateCount only), or federated-unavailable. Direct edges only — no transitive lineage, no embedded candidate arrays.
search_decisionsSearch the decision corpus (including the graveyard by default) by deterministic normalized literal substring over id, title, tags, and Markdown body. Optional status/scope (any-of) and tags (all-of) filters are ANDed. Returns bounded summaries only — no ranking, no model, no body.
Public scan report
scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it
- Code scan25 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 1 days ago15/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
What the publisher says
From the adrkit decision memory repository's README, as published. We do not edit it. Read it on GitHub
adrkit
Decision memory for human- and agent-authored plans — architecture decision records that are machine-readable, enforceable in CI, and legible to agents, without leaving git.
Most ADR tooling is a markdown template and a static site generator. That records a decision; it doesn't make the decision do anything. adrkit treats a record as typed data with a markdown body and adds one field — affects — so a tool can answer "which decisions govern this pull request?" and put the answer where the next decision is being made.
Decision governance, not generated documentation
Proposed interoperability direction: ADR-0037 is under review and has not been ratified.
Generated knowledge systems answer "how does the system work now?" adrkit answers "what did people decide, what alternatives were rejected, and which decisions govern this change?"
Tools such as OpenWiki can consume ADRs as evidence and turn them into browsable current-state documentation. That is complementary to adrkit: the generated wiki is a downstream read model, while the reviewed records in git retain authority over decision lifecycle and typed relationships. Machine verification of generated content is not human ratification of a decision.
See the provisional generated-knowledge guide for the OpenWiki setup being evaluated and the proposed ownership boundary between the two tools.
Quickstart
The CLI is published as @adrkit/cli and exposes the adr binary. Published artifacts target Node 22+:
npx @adrkit/cli lint # validate the corpus in docs/adr
npx @adrkit/cli explain src/payments/api.ts # which decisions govern this file?Or add it to a project (Bun-first repos can use bun add -D @adrkit/cli / bunx):
npm i -D @adrkit/cliThe pure library surfaces install independently: npm i @adrkit/core @adrkit/evaluator.
See the Quickstart guide and the full command reference.
Choose a starting point
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
Runs npx -y @adrkit/mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp -- npx -y @adrkit/mcp
adrkit decision memory: common questions
- Is adrkit decision memory MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the adrkit decision memory safety report
- How do I install adrkit decision memory?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does adrkit decision memory need an API key?
- No secret keys are declared. It reads 2 settings from the environment.
- Is adrkit decision memory maintained?
- The last commit was in the last day (2026-09-19). The latest release is v0.13.0.
- What can I use instead of adrkit decision memory?
- Servers from other publishers that do the same job: Lockstep MCP server, Total Agent Memory MCP server and Dvalincode MCP server. Compare all adrkit decision memory alternatives.
Alternatives to adrkit decision memory
Same job from other publishers: the closest match first, then the best rated.
LockstepDecision memory for AI coding agents: captures decisions once, briefs every agent before it acts.not reviewedGrowingA
Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA- DvalincodeDeterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.not reviewedGrowingA
- ProjectmemCoding agent memory — one local MCP server for every project. Warns before repeating failed fixes.not reviewedGrowingA
- rag-ratRepository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.not reviewedGrowingB
