Reported issues for Mindswap
Pod holds 10 of 10 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.
Back to Mindswap.
Most discussed
Add MCP distribution docs and marketplace listing plan
Summary
Add a distribution and docs plan for mindswap’s MCP server across the places people actually discover and use MCP servers.
Why this matters
Publishing metadata is only half the job. Users need clear install docs, supported-client guidance, and a listing strategy so the server is easy to find and easy to try.
Target surfaces
- GitHub MCP Registry
- Official MCP Registry
- PulseMCP
- GitHub repo README and landing page
- Optional enterprise/private registry guidance for inter
Read the thread · 2026-04-24 · closed · 1 comment
Add official MCP Registry publishing support and release metadata
Summary
Add official MCP Registry publishing support so mindswap can be discovered and installed through the official registry flow instead of only via direct npm package installation.
Why this matters
The MCP Registry is the canonical public metadata layer for MCP servers. Publishing there makes mindswap easier to discover, verify, and install across supported MCP clients and aggregators.
Proposed deliverables
- Add
mcpNameand registry metadata to the package - Generate and mai
Read the thread · 2026-04-24 · closed · 1 comment
Add structured MCP resources for stable context artifacts
Summary
Add first-class MCP resources so clients can read structured mindswap artifacts directly instead of only through the current text briefing.
Why this matters
The current MCP server exposes a small tool set, but the context is still mostly delivered as a synthesized text blob. That works, but it limits client-side UX, filtering, and incremental refresh. Resources are a better fit for stable artifacts that should be readable independently.
Proposed resources
- `mindswap://cont
Read the thread · 2026-04-24 · closed · 1 comment
Add MCP prompt templates for common handoff workflows
Summary
Add MCP prompt templates for the most common mindswap workflows so clients can invoke a stable, opinionated flow instead of hand-authoring prompts every time.
Why this matters
The server already knows how to summarize context, save sessions, search memory, and report health. Prompt templates make those capabilities discoverable and repeatable in clients that support MCP prompts.
Proposed prompts
start-session— gather current state, recent changes, conflicts, and next b
Read the thread · 2026-04-24 · closed · 1 comment
Add remote MCP transport for hosted and browser-based clients
Summary
Add a remote MCP transport mode so mindswap can run as a hosted MCP server instead of only stdio/local-editor integrations.
Why this matters
Today the server is mainly local stdio. That is good for editors, but it limits use cases like browser-based clients, remote agents, shared team workspaces, and hosted workflows that cannot spawn local processes.
Proposed transport features
- Optional HTTP/SSE or streamable HTTP transport
- Configurable auth for remote access
- Explici
Read the thread · 2026-04-24 · closed · 1 comment
Add structured memory CRUD for blockers, assumptions, and resolutions
Summary
Add a full CRUD layer for structured memory so mindswap can create, update, resolve, list, and delete blockers, assumptions, questions, resolutions, and related session notes through MCP and the CLI.
Why this matters
The current structured memory model stores important context, but the write surface is still narrow. Teams and AI clients need a real memory API so they can mark items resolved, update blockers, and keep a clean project memory over time.
Proposed capabilities
Read the thread · 2026-04-24 · closed · 1 comment
Generate machine-readable interface contracts for agent handoff
Summary
Add machine-readable interface contracts so one AI agent can hand off module expectations, blockers, and boundaries to another without requiring a full source-code reread.
Problem
Markdown handoffs are useful, but they are still primarily human-oriented. For coordinated multi-agent work, mindswap should be able to emit structured contracts for active modules or workflows.
Proposed solution
Generate JSON contracts that capture:
- active module boundaries
- expected inputs a
Read the thread · 2026-04-23 · closed · 1 comment
Add semantic ask command backed by local vector retrieval
Summary
Add a new mindswap ask command that answers natural-language questions from project memory using semantic retrieval instead of only keyword matching.
Problem
The repo already has mindswap_search, but long histories and decisions become harder to query as the project grows. Users should be able to ask questions like:
- Why did we choose this auth approach?
- What did we decide about payments?
- What blocker stopped the last session?
and get a synthesized answer with source
Read the thread · 2026-04-23 · closed · 1 comment
Most recent
Refine MCP and CLI for performance, latency, and discovery readiness
Summary
We already have the core CLI, MCP server, memory model, sync, and registry support. The next major step is not adding more surface area. It is refining the existing tools so they are faster, lighter, and more reliable, while also making the product easier to discover and understand on the web.
Why this matters
The current product works, but the user experience can still be improved in the places that matter most:
- tool calls should return faster and with less token overhead
Read the thread · 2026-04-25 · closed · 0 comments
Upgrade mindswap_search to support semantic retrieval over project memory and history
Summary
Make mindswap_search meaningfully useful for AI agents by moving beyond simple keyword matching.
Problem
Searching project continuity data is one of the highest-value MCP actions, but plain text matching will not scale well as memory/history grows.
Users and agents need answers to questions like:
- why did we choose this auth approach?
- what happened last time we touched payments?
- what blockers were found during the last failing test run?
These queries are often semantic
Read the thread · 2026-04-23 · closed · 1 comment
The remaining reports are on the project's issue tracker.