Continuity Evidence MCP server
io.github.zerohourzulu/continuity-evidence·v0.3.0-preview.12A bounded local evidence tool with current agent permission checks and durable retry handling.
0 stars69 downloads/wk
Reviews
Write oneNobody has reviewed Continuity Evidence yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Continuity Evidence tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
continuity_collect_evidenceCopy the operator-selected files into a protected evidence packet if the launch-bound runtime still has permission. Keep one operationId for retries; uncertain results are reconciled, never resubmitted. This does not prove the contents true.
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- Code scan7 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 21 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Continuity Evidence compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 4,460 AI and agents servers
- Tools
- 1
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 69
- more than 54% of 1,538 AI and agents servers with a package
What its tools let an agent do: 1 read
Release history: 5 versions in the registry since 2026-09-22, latest 2026-10-10, typically one every 2 days.
Install Continuity Evidence in Claude Code, Cursor or VS Code
Runs npx -y @ramex-labs/continuity-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add continuity-evidence -- npx -y @ramex-labs/continuity-mcp
What the publisher says
From the Continuity Evidence repository's README, as published. We do not edit it. Read it on GitHub
Core 0.3 preview: Build a fresh case, try the protected MCP tool, or run the public tests. The original 0.2.2 evaluation releases remain available.
Continuity — agents change; responsibility remains
Explore the interactive demo → · Start here · Developer guide · Security and limits
Developer preview · Apache 2.0. Release status.
A process supervisor can start Agent B. Continuity records which role B occupies, which powers it has, what happened before, and which unfinished duties survive the change. A replacement receives its explicitly granted powers; an unfinished duty does not silently grant more authority.
The demonstration follows a security investigation interrupted by an agent replacement. The old request is refused, the investigation stays OPEN, and the successor’s review permission is checked independently.
Choose your path
Run the tutorial
Use Node 22.18+ (22.x), 24.x or 26.x on macOS or Linux. Prefer the latest patch of your chosen release. No global pnpm or Python is needed for this tutorial. Full quickstart, including archive extraction.
Get the public source; no GitHub account is needed:
<!-- quickstart:clone -->
git clone https://github.com/zerohourzulu/continuity.git
cd continuity<!-- /quickstart -->
See the result first, without installing dependencies:
<!-- quickstart:recorded -->
node examples/recorded.mjs<!-- /quickstart -->
Expect ALLOW for reviewing the investigation and DENY for collecting another packet. This inspects a bundled recorded case; it does not execute a new action.
Generate your own evidence:
<!-- quickstart:run -->
node tools/setup.mjs
node tutorial/start.mjs<!-- /quickstart -->
Expect PASS — duty remains OPEN; B has no collection power, then VERIFIED. Setup downloads locked dependencies with scripts disabled. The tutorial then runs locally using synthetic data and public test keys. It prints your new case name and exact follow-up commands. Rerunning creates another case and preserves earlier evidence.
Change one permission:
<!-- quickstart:compare -->
node tutorial/start.mjs --deny-review<!-- /quickstart -->
B still inherits the duty, but its review permission becomes DENY. Expected output and explanation · Setup checks and recovery.
Choose your holder of record.
Keep records locally, or choose a chain-backed deployment to make selected history publicly verifiable. Cryptographic commitments can let authorized reviewers check private records without publishing their contents. This tutorial runs locally; each deployment has its own privacy, availability and finality requirements.
Explore and build
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Continuity Evidence: common questions
- Is Continuity Evidence MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Continuity Evidence safety report
- How do I install Continuity Evidence?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Continuity Evidence need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Continuity Evidence maintained?
- The last commit was 23 days ago (2026-10-12). The latest release is v0.3.0-preview.12.
- What can I use instead of Continuity Evidence?
- Servers from other publishers that do the same job: HOL Guard MCP server, Agent-Native Chat MCP server and Watch Skill MCP server.
- How does Continuity Evidence compare with other AI and agents MCP servers?
- safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 1 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Continuity Evidence
Same job from other publishers: the closest match first, then the best rated.
- HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.not reviewedEstablishedA
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- Watch SkillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work.not reviewedEstablishedB
- OpenWorkProofVerifiable agent evidence; opt-in Codex guard and reference SOC alert review.not reviewedEstablishedA
- KilnSpawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.not reviewedEstablishedB