entangled-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| entangled_announceC | [ENTANGLED] Announces or heartbeats this agent CLI in the shared swarm. Example: entangled_announce(agent_id='antigravity-gemini', client_type='antigravity-cli', current_workspace='/path', active_task='Refactor') |
| entangled_get_swarmA | [ENTANGLED] Discovers all active agent CLIs in the entangled swarm, their client type, current workspace, last heartbeat, and active task. Use this to see who else is working. |
| entangled_broadcast_knowledgeB | [ENTANGLED] Shares knowledge, findings, bug root-causes, or architecture decisions across ALL agent CLIs. Once broadcasted, Opencode, Antigravity, Claude Code, or DeepSeek can read and leverage it. |
| entangled_query_knowledgeA | [ENTANGLED] Searches shared knowledge across all agent sessions by topic, tag, or keyword. Use this before tackling a task to check if another agent CLI has already investigated or solved it. |
| entangled_send_messageC | [ENTANGLED] Sends an asynchronous direct message or task delegation to another agent CLI (or 'all'). Example: Antigravity sends an action_request to 'opencode' to run a backend test. |
| entangled_check_inboxB | [ENTANGLED] Checks the inbox for incoming messages or instructions sent to this agent CLI. Call this at the beginning of a session or task to see if another agent requested work. |
| entangled_acquire_lockB | [ENTANGLED] Acquires an exclusive mutex lock on a file, directory, or critical task. Prevents multiple agent CLIs from editing the same file concurrently and causing merge conflicts. Locks automatically expire after ttl_seconds (default 30 minutes). |
| entangled_release_lockB | [ENTANGLED] Releases an exclusive lock once an agent CLI has finished modifying a resource. |
| entangled_list_locksA | [ENTANGLED] Lists all currently active resource locks across the entire workspace. |
| entangled_get_activity_feedC | [ENTANGLED] Retrieves the unified chronological activity feed of what all agents in the swarm have done. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_resource_swarm_status | |
| get_resource_activity_feed |
TDQS
Scored across 10 tools
Each tool has a distinct purpose: presence (announce, get_swarm), knowledge (broadcast, query), messaging (send, check), locks (acquire, release, list), and activity feed. Descriptions clarify boundaries, and no two tools overlap significantly.
All tools use consistent snake_case with an 'entangled_' prefix and a verb_noun pattern (e.g., acquire_lock, send_message). 'announce' is a verb-only outlier but still fits the predictable action-oriented style.
10 tools cover the multi-agent coordination domain well without redundancy; each tool earns its place. The set is well-scoped for the server's stated purpose.
Core operations are covered: knowledge sharing (broadcast/query), messaging (send/check), locks (acquire/release/list), presence, and activity feed. Minor gaps include no update/delete for knowledge or messages, and no explicit leave-swarm or lock-renew operation.