Handover MCP server
online · 100% uptimesh.handover/handover·v1.18.0·1 starsShared, versioned context that humans and AI agents can publish, review, annotate, and continue.
1 stars
Reviews
Write oneNobody has reviewed Handover yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Handover tools (17, 3 write)
write = sends, deletes, buys or postshandover.annotateFreeAdd a durable comment anchored to selected text or lines in an immutable artifact revision. Read the artifact first and preserve the exact quote and surrounding context.
handover.annotationsFreeRead revision-anchored file comments, selected text, status, authorship, and resolution metadata. Use status=open to find feedback that still needs action.
handover.assignFreeReplace the open assignments with the supplied collaborator identities. This changes collaboration state, not the immutable handover revision.
handover.commentFreeAppend a discussion comment and optionally notify explicitly mentioned collaborators.
handover.continueFreeAppend an immutable revision after reading the current snapshot. expectedRevisionId is mandatory to prevent overwriting another collaborator's work. Omitted artifacts are inherited; matching names are replaced.
handover.createwrite actionFreeCreate durable shared context with an initial immutable revision. Authorship comes from the authenticated Handover identity.
handover.getFreeRead a handover snapshot, continuation brief, artifact metadata, and revision history. Omit revisionId for the current snapshot.
handover.okf.exportFreeExport a handover revision as an Open Knowledge Format bundle for another human or agent system.
handover.okf.importFreeImport Open Knowledge Format files into a new immutable Handover revision. Replaying the same bundle is idempotent.
handover.publicationFreeRead the stable report URL, entry file, access mode, and selected revision for a handover.
handover.publishwrite actionFreeCreate or update a stable /r/{slug}/ report projection of a Handover revision.
handover.pullFreeReturn the selected files of a published report with paths, hashes, media types, and UTF-8 or base64 content.
handover.read_artifactFreeRead bounded artifact content after inspecting a handover. Text is returned as UTF-8 and binary content as base64; truncated results report that explicitly.
handover.searchFreeFind current shared context with hybrid, semantic, or lexical retrieval across metadata and artifact content. Use an empty query to list recent handovers.
handover.threadFreeRead comments, explicit mentions, assignments, and eligible collaborators without changing revision history.
handover.update_commentwrite actionFreeEdit an authored comment, or resolve/reopen an annotation. Set resolvedRevisionId when a new handover revision addressed the feedback.
handover.whoamiFreeReturn the authenticated person or service agent, organization, workspace, role, and granted scopes. Call this before reading or publishing to confirm attribution and tenancy.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 777ms20/20
- Tool poisoning17 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 3 write-action tools with no auth3/15
- Maintenancelast push 50 days ago12/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year6/10
Findings (1)
- highWrite-action tools reachable without authentication
auth.open-write
How Handover compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 75/100
- higher than 45% of 48,255 servers
- Tools
- 17
- the typical server has 7
- Tools that change things
- 18%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 251 ms
- faster than 55% of 30,031 servers
- GitHub stars
- 1
- more than 65% of 28,688 servers
What its tools let an agent do: 12 read · 1 create · 2 change · 2 send or post
Install Handover in Claude Code, Cursor or VS Code
claude mcp add --transport http handover https://handover.sh/api/mcp?profile=core
What the publisher says
From the Handover repository's README, as published. We do not edit it. Read it on GitHub
Handover MCP
Move active work between Claude Code, Codex, Cursor, Gemini CLI, people, and service agents without losing decisions, files, history, or authorship.
Handover provides shared, versioned context for humans and AI agents through a hosted Model Context Protocol server, a dependency-free CLI, and eight open Agent Skills. This repository is the public source, discovery, installation, and connection record for those interfaces.
Research and evidence
The Handover research and evidence index collects the open continuity benchmark, Reporter migration field report, Handoff Continuity Record, and runnable continuation demo. Findings stay beside their methods, source artifacts, first-party relationship, and material limitations.
The versioned research/v1/ package gives agents and researchers a stable JSON index, JSON Schema, citation metadata, and a bounded Markdown summary. The package is a first-party publication by Handover and 44pixels; it is designed for inspection and reuse, not presented as independent validation.
- Human research index
- Agent-readable production index
- Versioned repository index
- Citation metadata
- Run and submit an independent benchmark result
See a complete handoff
The public continuation demo shows the same workflow from both sides: an interactive human view and an agent-readable record. It includes Markdown, SQL, JSON, a visual artifact, three attributable revisions, a human review note, and the next agent's resolution. No account is required.
- Interactive demo
- Continue the demo in your workspace
- Demo workflow and verification notes
- Agent-readable manifest
- Raw Markdown
- Raw SQL
- Evidence JSON
Build a private handoff prompt
The AI handoff prompt generator turns unfinished work into separate capture and receiver prompts without requiring an account. Draft fields stay inside the browser tab and are not sent to analytics or stored as a server-side draft.
The receiver prompt requires the next actor to inspect the evidence, separate verified and unverified state, identify blockers, and state one bounded next action before continuing. Copy or download the Markdown record, or carry the same private draft into a prefilled first handover.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Handover: common questions
- Is Handover MCP server safe?
- Mostly: it is graded B (75/100). Read the Handover safety report
- How do I install Handover?
- It runs remotely at handover.sh. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Handover need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Handover maintained?
- The last commit was 91 days ago (2026-08-05). The latest release is v1.18.0.
- Is Handover up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Handover compare with other MCP servers?
- safety score 75/100 (higher than 45% of 48,255 servers); tools 17 (the typical server has 7); tools that change things 18% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.