Agent Comms MCP server

by ExaDev·io.github.ExaDev/agent-comms·v4.5.0

Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP

A94/100grade A

What users say

No reviews yet

Safety scan

A94/100

not scanned yet

Adoption

Established

21 stars16k downloads/wk

Reviews

Nobody has reviewed Agent Comms yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

No tool declarations could be read from the package source. They show once the server is installed.

Not scanned yet. New registry listings are scanned within a day of import.

Runs npx -y agent-comms on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-comms -- npx -y agent-comms

Is Agent Comms MCP server safe?: Yes, by our scan: it is graded A (94/100). Read the Agent Comms safety report
How do I install Agent Comms?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Agent Comms need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent Comms maintained?: The last commit was in the last day (2026-09-19). The latest release is v4.5.0.
What can I use instead of Agent Comms?: Servers from other publishers that do the same job: Linksee Memory MCP server, Mockserver MCP server and Google Surf MCP server. Compare all Agent Comms alternatives.

Same job from other publishers: the closest match first, then the best rated.

Linksee Memory
Hand a project over with the reasons attached. Local-first cross-agent memory MCP + drift detection.
not reviewed
Growing
A
Mockserver
Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
not reviewed
Established
A
Google Surf
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
not reviewed
Established
B
PDF
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
not reviewed
Established
A
CHAP Coordinator
Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
not reviewed
Established
A