Skip to main content

visionlog.md

MCP server for long-term project governance. Records vision, goals, guardrails, SOPs, and architectural decisions (ADRs) — the contracts that all execution must honor.

Part of the trilogy: research.md → visionlog.md → ike.md

  • research.md earns decisions with evidence
  • visionlog.md records them as binding contracts
  • ike.md executes within those contracts

What it enforces

  • Guardrails are active or deprecated — never deleted
  • ADRs are permanent once accepted — a new ADR supersedes, never overwrites
  • Goals form a DAG — dependencies must be resolved before a goal is available
  • Vision is sticky — it does not drift session to session

Trilogy conventions

visionlog.md follows shared conventions with ike.md and research.md. See CONVENTIONS.md for the full standard.

  • Config lives at .visionlog/config.yaml (committed to git)
  • Tools: project_init (new project) and project_set (register existing for session)

Install

Not yet published to npm. Install from local path.

npm install
npm run build

Add to .mcp.json:

{
  "mcpServers": {
    "visionlog": {
      "command": "/absolute/path/to/visionlog.md/dist/visionlog",
      "args": ["mcp", "start"]
    }
  }
}

Session protocol

project_set { path: "/path/to/project" }   <- returns project_id
visionlog_boot { project_id: "..." }        <- active guardrails + goal state
visionlog_guide { project_id: "..." }       <- vision + decisions + goal map

Read both visionlog_boot and visionlog_guide at the start of every session before touching any task or code.

Project structure

my-project/
  .visionlog/
    config.yaml          <- project GUID + metadata (commit this)
    vision.md            <- north star, anti-goals, success criteria
    goals/               <- GOAL-NNNN.md — DAG of milestones
    adr/                 <- ADR-NNNN.md — architectural decisions
    guardrails/          <- GUARD-NNNN.md — active constraints
    sops/                <- SOP-NNNN.md — coordination protocols

Tools

Session

Tool Description
project_init Initialize visionlog in a new project
project_set Register existing project for session, returns project_id

Orientation (call at session start)

Tool Description
visionlog_boot Active guardrails + current goal state + backlog check
visionlog_guide Vision + key decisions + full goal map
visionlog_status Counts: goals, decisions, guardrails, SOPs

Vision

Tool Description
vision_view Read the project vision
vision_set Set or update the vision document

Goals

Tool Description
goal_create Add a goal to the DAG
goal_list List all goals with status
goal_view Read a goal
goal_update Update goal status or body
goal_unlockable List goals whose dependencies are met

Decisions (ADRs)

Tool Description
decision_create Record an architectural decision
decision_list List all ADRs
decision_view Read an ADR
decision_update Update status or body

Guardrails

Tool Description
guardrail_create Add a guardrail
guardrail_list List all guardrails
guardrail_view Read a guardrail
guardrail_update Update status or body
guardrail_inject Inject guardrails into an existing prompt

SOPs

Tool Description
sop_create Add a standard operating procedure
sop_list List all SOPs
sop_view Read a SOP
sop_update Update status or body

Metadata

Release files for visionlog-md 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for visionlog-md 0.2.0
File Size Uploaded Provenance
visionlog_md-0.2.0.tar.gz 93.1 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for visionlog-md 0.2.0
File Interpreter ABI Platform
visionlog_md-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 112.6 kB

Release files / visionlog_md-0.2.0.tar.gz

Download URL visionlog_md-0.2.0.tar.gz
Size 93.1 kB
Tags Source
SHA-256 checksum
How to use checksums
65f263e2836e626462eae3b2f336fb823e2df8c190840b010cbcf3367e5b196d
BLAKE2b-256 checksum
How to use checksums
50621ed5ec4765d28b30bc306c824299e0ce9489448cf99ecce35fe74f4a9888
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 22, 2026.

Transparency log

Release files / visionlog_md-0.2.0-py3-none-any.whl

Download URL visionlog_md-0.2.0-py3-none-any.whl
Size 19.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b72fa7f76f1ed0c934e2b38fccce79be462e488d0f81ea36884e782b4cac242f
BLAKE2b-256 checksum
How to use checksums
ec59445c366c28b5cdb7fd96c11309abece01baf0c62c4afee4393b886fe5259
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 22, 2026.

Transparency log

Security for visionlog-md 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for visionlog_md-0.2.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 22, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page