MindSync MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MINDSYNC_HOME | No | Local data root | ~/.mindsync |
| MINDSYNC_SSH_HOST | No | SSH host; empty disables remote | |
| MINDSYNC_REMOTE_ROOT | No | Remote project root; empty disables remote | |
| MINDSYNC_SSH_TIMEOUT | No | SSH connect timeout (seconds) | 3 |
| MINDSYNC_LOCK_TIMEOUT | No | Local lock wait (seconds) | 5 |
| MINDSYNC_REMOTE_ENV_FILE | No | Optional file sourced on remote before commands | config/mindsync.env |
| MINDSYNC_FOCUS_STALE_SECS | No | Ignore older focus entries | 7200 |
| MINDSYNC_REMOTE_CACHE_TTL | No | Cache TTL for online probe | 30 |
| MINDSYNC_REMOTE_TRUTH_SUBDIR | No | Markdown summaries directory | compiled-truth |
| MINDSYNC_REMOTE_WRITE_SCRIPT | No | Relative to remote root | tools/mindsync_fact.py |
| MINDSYNC_REMOTE_CONSOLIDATE_SCRIPT | No | Relative to remote root | tools/mindsync_consolidate.py |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_sync_contextA | Load local session state + compiled truth. Optionally pull remote truth first. Offline-first: always returns local data even if remote is unreachable or disabled. |
| update_focusC | Update this agent's focus and warn on overlaps with other non-stale agents. |
| queue_durable_factC | Write a durable fact remotely if online; otherwise queue locally for later flush. |
| sync_offline_factsC | Flush the offline queue to remote, optionally consolidate + pull compiled truth. |
| pull_truthC | Pull compiled-truth markdown from the remote host into the local cache. |
| delegate_taskA | Delegate a task to a headless CLI agent or role. The default agent='auto' selects an installed worker by capability. Pass required_capabilities when the orchestrator already knows what the task needs, and exclude_agents to keep the human-facing orchestrator out of the worker pool. Direct agent selection and static roles remain available as explicit overrides. If worktree is True, the agent runs in an isolated git worktree branching from cwd. checks are shell commands run after the agent finishes (for example a test command); read their outcome with job_review before spending anything on the job's output. memory_mode controls dispatch memory: auto (the default) infers an opaque Git checkout identity when no project is supplied, explicit requires memory_project, and off disables memory. An explicit project overrides inference. Raw prompts are never stored in memory. on_limit='handoff' is opt-in and requires worktree=True; only a configured, provider-specific quota signature can rotate to another available agent. |
| route_taskB | Preview automatic worker selection without launching a job. |
| get_orchestration_policyB | Read automatic delegation policy. Call when deciding whether to delegate or offer it. |
| healthB | Report local paths, queue depth, and remote reachability. |
| memory_bootstrapB | Retrieve bounded project context, prioritizing open and recent sessions. |
| memory_recallC | Recall related project facts with a loopback-only embedding model. |
| jobC | Job lifecycle: status, wait, result, review, or cancel. |
| eventsC | Event bus: publish, poll, or subscribe. |
| sessionC | Local memory session: start, checkpoint, or end. |
| memory_consolidationC | Fact consolidation: preview, apply, undo, or list. |
| listC | Orchestrator catalog: agents, models, or roles. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 16 tools
Several tool pairs blur together: get_sync_context and pull_truth both pull remote truth, memory_bootstrap and memory_recall both retrieve memory, and route_task plus get_orchestration_policy both serve delegation decisions. The descriptions help clarify intent, but an agent could easily select the wrong tool when aiming for a sync or memory operation.
Naming follows three conventions: verb_noun for most sync/delegation tools (queue_durable_fact, sync_offline_facts, delegate_task), bare nouns for infrastructure tools (health, job, events, session, list), and a memory_ prefix group (memory_bootstrap, memory_recall, memory_consolidation). Each pattern is readable on its own, but the mix makes the overall surface feel inconsistent.
At 16 tools, this sits at the start of the heavy band (16-25) and spans four distinct domains: sync/facts, memory, delegation/orchestration, and events. The breadth is defensible for a unified agent-sync server, but several tools could have been consolidated, pushing it slightly past a well-scoped 3-15 tool set.
Core lifecycles are well covered: offline fact queueing and flushing, memory sessions with consolidation undo, delegation preview/execute with job lifecycle, and event pub/sub. Minor gaps exist, such as a read-only orchestration policy with no setter, no way to delete a durable fact, and no offline-queue inspection beyond depth in health, but agents can work around these.