Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Mindswap

NPM · MINDSWAP · SCANNED SEP 24

Local-first AI context and memory server for cross-tool coding continuity.

Available components

0 this week 80 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 49 of 148 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 759 tokens (~84/item across 9 items; 4 tools + 5 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Mindswap MCP server?

Mindswap runs locally as an npm package, launched with npx -y mindswap. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · mindswap

# add to Claude Code
claude mcp add shiporbleed-mindswap -- npx -y mindswap
// .cursor/mcp.json
{
  "mcpServers": {
    "shiporbleed-mindswap": {
      "command": "npx",
      "args": [
        "-y",
        "mindswap"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "shiporbleed-mindswap": {
      "command": "npx",
      "args": [
        "-y",
        "mindswap"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add shiporbleed-mindswap -- npx -y mindswap
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "shiporbleed-mindswap": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mindswap"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add shiporbleed-mindswap --command npx --arg -y --arg mindswap
# ~/.hermes/config.yaml
mcp_servers:
  shiporbleed-mindswap:
    command: "npx"
    args: ["-y", "mindswap"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "shiporbleed-mindswap": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mindswap"
      ]
    }
  }
}
# add to Vellum
assistant mcp add shiporbleed-mindswap -t stdio -c npx -a -y mindswap
// mcp.json
{
  "mcpServers": {
    "shiporbleed-mindswap": {
      "command": "npx",
      "args": [
        "-y",
        "mindswap"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 24 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 22 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 18 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
    • Security disclosure: fail → unverified ▼ functional
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Analysed npm/mindswap@3.3.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 148 packages
Packages resolved 148
Deprecated 1
Stale 48
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~677 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
mindswap_get_context ~120

Get complete project context for this coding session. Call this FIRST when starting work on a project. Returns: project info, current task, recent decisions, what's in-progress, conventions, conflicts, and test status — all synthesized into a single briefing.

NameTypeReqDescription
compactboolean–Return token-optimized compact format (fewer tokens, same info)
focusstring–What to focus on: "all" for full context, "task" for current work only, "decisions" for architecture decisions, "recent" for latest changes

No output schema declared.

No examples provided.

mindswap_memory ~246

Manage structured memory items. Use this to list, add, update, resolve, archive, or delete blockers, assumptions, questions, and resolutions.

NameTypeReqDescription
actionstringyesOperation to perform on memory
afterstring–Only include items created after this timestamp
authorstring–Author for add/update or filtering
beforestring–Only include items created before this timestamp
globalboolean–Use global personal memory scope
hardboolean–Hard delete instead of archiving
idstring–Memory item id for get/update/resolve/archive/delete
jsonboolean–Return JSON instead of formatted text
limitinteger–Max number of items to return when listing
messagestring–Message for add/update
scopestring–Memory scope: repo, global, or all. Writes require repo or global.
sourcestring–Source for add/update or filtering
statusstring–Status for add/update or filtering
tagstring–Tag for add/update or filtering
typestring–Memory type for add or filtering

No output schema declared.

No examples provided.

mindswap_save_context ~178

Save session context before ending work or when significant progress is made. Records what was accomplished, decisions made, and what should happen next. This ensures the next AI session (in any tool) can pick up seamlessly.

NameTypeReqDescription
assumptionsarray–Assumptions made during this session that should carry forward
blockerstring–Any blocker or issue discovered
decisionsarray–Key decisions made during this session (e.g., "chose JWT over sessions for stateless API")
next_stepsarray–What should be done next
questionsarray–Open questions that remain unresolved
resolutionsarray–Resolved items or conclusions reached during this session
summarystringyesBrief summary of what was done in this session
task_statusstring–Update task status

No output schema declared.

No examples provided.

mindswap_search ~133

Search project context for specific information. Use when you need to know about a past decision, convention, or what happened with a specific feature. Searches decisions log, session history, and project state.

NameTypeReqDescription
globalboolean–Search global personal memory
querystringyesWhat to search for (e.g., "auth", "database choice", "why Redis")
scopestring–Search scope: repo, global, or all
typestring–Where to search: "all" searches everything, "decisions" only searches decision log, "history" only searches session history

No output schema declared.

No examples provided.

Common questions

What is the Mindswap MCP server?

Mindswap is an MCP server listed in the public MCP registry as io.github.ShipOrBleed/mindswap. Local-first AI context and memory server for cross-tool coding continuity. This page covers its npm package (mindswap).

Is the Mindswap MCP server safe to use?

Mindswap scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Mindswap MCP server expose?

Mindswap exposes 4 tools: mindswap_get_context, mindswap_save_context, mindswap_search, mindswap_memory. Their descriptions and schemas cost roughly 677 tokens of context every time the server is loaded.

Is the Mindswap MCP server still maintained?

Mindswap is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Mindswap MCP server under?

Mindswap declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.