Neo Agent Brain (Neo.mjs Agent OS MCP servers)

Five Neo.mjs Agent OS MCP servers: shared agent memory, repo knowledge, GitHub work, live app control

By neo.mjs JavaScript Local · stdio Knowledge and memoryGit and code hostingDeveloper tools

28 popularity score ★ 12 ↓ 60/wk

Connect your client

Local (from source)

Add in one click

Opens the app, which asks before it adds the server. Then replace each <NAME> in its settings with your value.

Or add it by command or config

FirstTerminal
git clone https://github.com/neomjs/neo-agent-brain.git
cd neo-agent-brain
npm install
Claude CodeTerminal
claude mcp add neo-agent-brain-neo-mjs-agent-os-servers -- node '<ABSOLUTE_PATH_TO_CLONE>/ai/mcp/server/memory-core/mcp-server.mjs'
Claude Desktopclaude_desktop_config.json
{
  "mcpServers": {
    "neo-agent-brain-neo-mjs-agent-os-servers": {
      "command": "node",
      "args": [
        "<ABSOLUTE_PATH_TO_CLONE>/ai/mcp/server/memory-core/mcp-server.mjs"
      ]
    }
  }
}
Cursor~/.cursor/mcp.json
{
  "mcpServers": {
    "neo-agent-brain-neo-mjs-agent-os-servers": {
      "command": "node",
      "args": [
        "<ABSOLUTE_PATH_TO_CLONE>/ai/mcp/server/memory-core/mcp-server.mjs"
      ]
    }
  }
}
VS Code.vscode/mcp.json
{
  "servers": {
    "neo-agent-brain-neo-mjs-agent-os-servers": {
      "type": "stdio",
      "command": "node",
      "args": [
        "<ABSOLUTE_PATH_TO_CLONE>/ai/mcp/server/memory-core/mcp-server.mjs"
      ]
    }
  }
}
Codex~/.codex/config.toml
[mcp_servers.neo-agent-brain-neo-mjs-agent-os-servers]
command = "node"
args = ["<ABSOLUTE_PATH_TO_CLONE>/ai/mcp/server/memory-core/mcp-server.mjs"]
Gemini CLITerminal
gemini mcp add --scope user neo-agent-brain-neo-mjs-agent-os-servers node -- '<ABSOLUTE_PATH_TO_CLONE>/ai/mcp/server/memory-core/mcp-server.mjs'

Settings 4

GEMINI_API_KEY Optional: Only for the remote Gemini embedding provider; the default route uses a local OpenAI-compatible endpoint.
NEO_TRANSPORT Optional: stdio (default) or streamable-http.
MCP_HTTP_PORT Optional: Port for streamable-http mode, 3001 by default.
NEO_MCP_ALLOWED_HOSTS Optional: Extra comma-separated hostnames allowed in streamable-http mode.

What it does

neo-agent-brain is the repository the Neo.mjs project uses to run its team of coding agents. It holds five separate MCP servers. Each one is a Node script in the checkout, and you start each one on its own.

Memory Core keeps memory across sessions and across agents. It stores turns and session summaries in ChromaDB, keeps a graph of decisions and work in SQLite, and also handles messages between agents, task hand-offs and presence. Knowledge Base indexes source code, guides, issues and pull requests into Chroma, then answers semantic queries or questions about them. GitHub Workflow covers issues, labels, assignees, pull-request diffs, formal reviews, reviewer requests, Projects and Discussions. Neural Link connects to a running Neo.mjs application, where it can inspect components, stores and state and change them: it can create or remove components, set properties, patch code and replay transactions. File System reads, writes and lists files in a sandbox, checks syntax and runs Playwright tests. The README says it is meant for harnesses that lack their own file tools.

In total the servers define 156 tools: 52 in Memory Core, 13 in Knowledge Base, 24 in GitHub Workflow, 60 in Neural Link and 7 in File System. These counts come from each server's openapi.yaml, which is the tool contract the server loads; the README gives no counts. Memory Core talks over stdio by default. Setting NEO_TRANSPORT=streamable-http makes it serve HTTP on port 3001, which MCP_HTTP_PORT can change (memory-core configBase.mjs).

What it needs

RuntimeNode.js 24+

Node.js 24 or newer, Git, and a clone of the repository with `npm install` run in it. The package is private and not on npm. Memory Core and Knowledge Base need a running ChromaDB and an embedding provider. The default is a local OpenAI-compatible endpoint; Ollama or Gemini (with GEMINI_API_KEY) can be used instead. GitHub Workflow signs in through an authenticated `gh` CLI. Neural Link needs a running Neo.mjs application connected to its bridge.

Limits

There are no releases yet: package.json is version 0.0.0 and work happens on the dev branch. Until Neo.mjs v13.2 ships, the Brain depends on a pinned commit of neomjs/neo. The README calls the Agent Institution app the operator-facing entry point and says running services from this root is a transitional path. The full two-way GitHub sync is not exposed as an MCP tool; it runs only as an npm script. Each server refuses to start when its local config overlay is stale. Chroma is the only vector store Memory Core supports.

Who it suits

It suits teams building on Neo.mjs, or running several long-lived coding agents that need shared memory, a semantic index of their repository and GitHub review tools, and who are willing to run ChromaDB and a local embedding model. Neural Link is useful only for Neo.mjs applications. If you want a single drop-in memory or GitHub server installed with one npx line, this is a poor fit: it is a whole source checkout with daemons, config overlays and no published package.

Tools 60 of 156

add_memory
Memory Core: save an agent turn to long-term memory
query_raw_memories
Memory Core: semantic search over stored memories
query_summaries
Memory Core: semantic search over session summaries
query_recent_turns
Memory Core: list the latest stored turns
get_session_memories
Memory Core: fetch all memories of one session
get_all_summaries
Memory Core: list session summaries
resume_session
Memory Core: pick up a previous session
purge_session
Memory Core: delete a session's stored data
get_context_frontier
Memory Core: read the current priority frontier from the graph
mutate_frontier
Memory Core: change the priority frontier
search_nodes
Memory Core: search nodes in the knowledge graph
get_neighbors
Memory Core: list graph nodes linked to one node
query_hybrid_graph
Memory Core: combined vector and graph query
add_message
Memory Core: send a message to another agent
list_messages
Memory Core: list an agent's messages
delete_message
Memory Core: delete a stored message
transition_task
Memory Core: move a coordinated task to a new state
who_is_online
Memory Core: show which agents are active
grant_permission
Memory Core: grant an agent a permission
ask_knowledge_base
Knowledge Base: answer a question from the indexed repository
query_documents
Knowledge Base: semantic search over indexed source, docs and tickets
ingest_source_files
Knowledge Base: index source files
manage_knowledge_base
Knowledge Base: run maintenance on the index
get_class_hierarchy
Knowledge Base: show a Neo.mjs class inheritance tree
list_documents
Knowledge Base: list indexed documents
get_document_by_id
Knowledge Base: fetch one indexed document
list_issues
GitHub Workflow: list synced issues
create_issue
GitHub Workflow: open a GitHub issue
manage_issue_comment
GitHub Workflow: add or edit an issue comment
manage_issue_labels
GitHub Workflow: add or remove issue labels
manage_issue_assignees
GitHub Workflow: change issue assignees
manage_issue_projects
GitHub Workflow: add an issue to a GitHub Project or update its fields
update_issue_relationship
GitHub Workflow: set sub-issue or blocked-by links
list_pull_requests
GitHub Workflow: list pull requests
checkout_pull_request
GitHub Workflow: check out a pull request locally
get_pull_request_diff
GitHub Workflow: read a pull request diff
get_conversation
GitHub Workflow: read an issue or PR conversation
manage_pr_review
GitHub Workflow: post or update a formal PR review
manage_pr_reviewers
GitHub Workflow: request or remove PR reviewers
create_discussion
GitHub Workflow: start a GitHub Discussion
manage_discussion_comment
GitHub Workflow: comment on a Discussion
get_viewer_permission
GitHub Workflow: show the signed-in account's repo permission
get_component_tree
Neural Link: read the component tree of a running Neo.mjs app
query_component
Neural Link: find components by selector
get_instance_properties
Neural Link: read properties of an instance
set_instance_properties
Neural Link: change properties of an instance
create_component
Neural Link: add a component to the running app
remove_component
Neural Link: remove a component
inspect_store
Neural Link: read a data store's records
modify_state_provider
Neural Link: change a state provider's data
call_method
Neural Link: call a method on an instance
patch_code
Neural Link: replace a method's code at runtime
get_console_logs
Neural Link: read the app's console logs
simulate_event
Neural Link: fire a DOM event in the app
reload_page
Neural Link: reload the application page
read_file
File System: read a file in the sandbox
write_file
File System: write a file in the sandbox
list_directory
File System: list a sandbox directory
check_syntax
File System: check a file's syntax
run_playwright_test
File System: run a Playwright test

Similar servers