O

ops-brain MCP

Self-hosted team bus for AI agents: cross-machine handoffs, check-in, and shared knowledge on your own PostgreSQL. Reads keep Guard's usual

Self-hosted team bus for AI agents: cross-machine handoffs, check-in, and shared knowledge on your own PostgreSQL. Reads keep Guard's usual handling; writes to the shared bus and both deletes are gated on review. Off until you turn it on.

mcp.ops-brain · v1.0.0 · Specialized tools

By Community contributorExternal · opt-inMCP server
Try this coverage Install GuardView exact source Documentation Claim this coverage
0
Protection rules
0
Permission checks
1
Mapped commands
1

Overview

What this coverage does

Self-hosted team bus for AI agents: cross-machine handoffs, check-in, and shared knowledge on your own PostgreSQL. Reads keep Guard's usual handling; writes to the shared bus and both deletes are gated on review. Off until you turn it on.

Key facts

Catalog ID
mcp.ops-brain
Version
v1.0.0
Kind
MCP server
Category
Specialized tools
Protection rules
0
Permission checks
1
Mapped commands
1
Maintainer
Community contributor(community, provenance recorded)
Source commit
b53aa2d
Protection model
External · opt-in
External · opt-in

External coverage. It must be enabled through Guard controls; this page does not activate it.

Stated limits

  • Coverage is limited to the reviewed operations and the surrounding Guard policy.
  • A maintainer profile is not a security certification or an official upstream endorsement.

Command mapping

Every command this extension recognizes, with the catalog default floor Guard applies before workspace policy. Search the table, then open an operation for safe variants and the permission ID.

No per-command matchers are published for this listing. Coverage is described by the reviewed rule count, permission checks, and the surrounding Guard policy.

Tool state mapping

ToolGuard state
check_inInherit policy
search_busInherit policy
get_handoffInherit policy
list_handoffsInherit policy
list_replies_to_meInherit policy
create_handoffReview
accept_handoffReview
complete_handoffReview
mark_mergedReview
add_knowledgeReview
update_knowledgeReview
delete_knowledgeReview
delete_handoffReview
otherReview

Runtime identity

Catalog ID
mcp.ops-brain
Guard enforcement ID
command.mcp-ops-brain
Source path
contributions/mcp-servers/mcp.ops-brain.json
Contribution digest
sha256…3a56a6

Mapped executables

ops-brain

Action classes

mcp opsxhbrain tool

Technical profile

Independent technical profile

Published revision 1
Marketing distribution: off.This profile has no audience, channel, or promotion controls.
Profile content digest
sha256:537afb0160233a1206e668cd0e281d02fc055600f31d76a99e85daf8ecf79ff1
Profile source SHA
de657cda43e298852750116db3449773b1674fce
Source version
1.0.0
Native source path
contributions/mcp-servers/mcp.ops-brain.json
Native extension ID
mcp.ops-brain
Runtime extension ID
command.mcp-ops-brain
Contribution digest
sha256:a3ab1dbdcef39b6c875c3d1d70f0a966946b5bb4d5b4730ea41f31a3233a56a6
Source contract fingerprint
sha256:7c9260b5456d59026d87860688d2c210ef6ee987936c946c0e438a46bf991686

Native contribution

Supported by reviewed source projection

Source version

Supported by reviewed source projection

Runtime capability

Supported by reviewed source projection

Permissions

Supported by reviewed source projection

The reviewed catalog declares 1 extension permission(s).

  • check_in: inherit
  • search_bus: inherit
  • get_handoff: inherit
  • list_handoffs: inherit
  • list_replies_to_me: inherit
  • create_handoff: review
  • accept_handoff: review
  • complete_handoff: review
  • mark_merged: review
  • add_knowledge: review
  • update_knowledge: review
  • delete_knowledge: review
  • delete_handoff: review
  • other: review

Harness support

Unknown / self-reported

Contributor-supplied harness support text is not independently verified. Any MCP harness that can launch a local stdio server. The author has run ops-brain with Claude Code, Codex, Grok, Antigravity CLI (Gemini) and Grok Bot.

  • Any MCP harness that can launch a local stdio server. The author has run ops-brain with Claude Code, Codex, Grok, Antigravity CLI (Gemini) and Grok Bot.
  • Linux and macOS, amd64 and arm64 (multi-arch image ghcr.io/thek3nsai/ops-brain, plus a static binary).
  • This Guard entry matches only the stdio command `ops-brain`. Self-hosted HTTP deployments (streamable HTTP with per-agent bearer tokens) aren't matched; set those up on Guard's Protect page.

Prerequisites

Unknown / self-reported

Contributor-supplied prerequisite text is not independently verified. PostgreSQL with the pgvector extension (the project uses pgvector/pgvector:pg18).

  • PostgreSQL with the pgvector extension (the project uses pgvector/pgvector:pg18).
  • DATABASE_URL pointing at that database. ops-brain runs its migrations on start.
  • Optional: an embeddings provider for hybrid search. Without it, search falls back to full-text.

Expected outcomes

Unknown / self-reported

Self-hosted team bus for AI agents: cross-machine handoffs, check-in, and shared knowledge on your own PostgreSQL. Reads keep Guard's usual handling; writes to the shared bus and both deletes are gated on review. Off until you turn it on.

Limitations

Supported by reviewed source projection

Limitations are copied from the reviewed catalog facts. Contributor-supplied limitation notes are not independently verified. Coverage limits declared in the reviewed catalog appear automatically when this guide is published.

  • Coverage is limited to the reviewed operations and the surrounding Guard policy.
  • A maintainer profile is not a security certification or an official upstream endorsement.

Residual effects

Unknown / self-reported

No residual-effect evidence was supplied.

Release evidence

Unknown / self-reported

Accepted contributors recorded in the reviewed catalog: @TheK3nsai (author).

Controlled fixture proof (separate)

Unknown / self-reported

No controlled fixture proof has been supplied.

Exact installation and activation guide

Commands are copied only when the reviewed source supplies an exact argv contract. Other guidance is labeled unknown and is not executed by this page.

Install

Unknown / self-reported

Contributor-supplied install guidance is not independently verified because an exact reviewed argv contract is unavailable. Get ops-brain: the release binary from https://github.com/TheK3nsai/ops-brain/releases or `docker pull ghcr.io/thek3nsai/ops-brain:v6.3.0`.

  1. 1

    Get ops-brain: the release binary from https://github.com/TheK3nsai/ops-brain/releases or `docker pull ghcr.io/thek3nsai/ops-brain:v6.3.0`.

    Self-reported / unavailable
  2. 2

    Register it in your harness as a stdio MCP server: command `ops-brain`, env DATABASE_URL.

    Self-reported / unavailable
  3. 3

    In HOL Guard, turn on the mcp.ops-brain entry (opt-in, off by default).

    Self-reported / unavailable

Activation

Unknown / self-reported

No activation procedure was supplied in the reviewed source.

Safe fixture inputs

Unknown / self-reported

Contributor-supplied safe fixture input guidance is not independently verified because an exact reviewed argv contract is unavailable. Use a throwaway database for the first run.

  1. 1

    Use a throwaway database for the first run.

    Self-reported / unavailable
  2. 2

    Ask the agent to call check_in. It's read-only, so Guard lets it through with normal handling.

    Self-reported / unavailable
  3. 3

    Ask it to create_handoff addressed to itself. Guard should stop it for review. Approve it, then call list_handoffs to see it.

    Self-reported / unavailable
  4. 4

    Ask it to delete_handoff on that test handoff. Guard should stop it again. If you approve, the row is deleted for good and an audit_log record is written.

    Self-reported / unavailable

Disable / remove

Unknown / self-reported

No disable/remove procedure was supplied in the reviewed source.

FAQ

Frequently asked questions

Self-hosted team bus for AI agents: cross-machine handoffs, check-in, and shared knowledge on your own PostgreSQL. Reads keep Guard's usual handling; writes to the shared bus and both deletes are gated on review. Off until you turn it on. The listing declares 0 rules and 1 permission check, with per-tool mapping for 14 tools. No per-command matchers are published for this listing.. Coverage is limited to these reviewed operations and the surrounding Guard policy.

External · opt-in: External coverage. It must be enabled through Guard controls; this page does not activate it. Enabling state is always controlled through Guard policy, never from this directory.

This listing entered the catalog as a community contribution through a public pull request with recorded provenance, with public credit to @TheK3nsai, and 1 GitHub maintainer is recorded on the listing. Credit is attribution only. A verified publisher profile and the claim flow verify authority separately; neither is an upstream endorsement or a HOL safety certification.

No. Every listing documents source, activation model, maintainer identity, and stated limitations so you can evaluate coverage before enabling it. Review the stated limitations and the exact source tree before relying on any single control.

This listing does not publish per-command matchers. Exact behavior follows your Guard policy combined with this entry's 0 rules and 1 permission check.

External coverage. It must be enabled through Guard controls; this page does not activate it. Enablement is managed through your workspace's Guard policy and controls — never from this directory. Open the install guidance for the setup flow, then adjust the MCP coverage for mcp.ops-brain in Guard's policy surface.

The matching action is stopped at Guard's pre-action boundary before it executes, and the decision is recorded with evidence your workspace can review. Exact behavior follows your Guard policy combined with this entry's 0 rules and 1 permission check.

No. Guard is local-first: interception, decisions, and evidence stay on your machine unless your workspace explicitly configures cloud features. This page is documentation only — it never executes a command or changes protection state.

Guard runs locally alongside the major AI coding agents and MCP-capable harnesses, so this coverage applies wherever Guard intercepts actions. See the supported harness guides at https://hol.org/guard/harnesses for per-tool approval behavior and limitations.

Guard has a free local tier that includes command interception, evidence, and the policy controls this listing documents. Team plans add shared policy, review queues, and audit surfaces. Current plans: https://hol.org/guard/pricing

Open an issue or pull request against the hol-guard repository, where the canonical catalog lives: https://github.com/hashgraph-online/hol-guard Listings are corrected through the same public review process that adds them.

Yes. Community extensions are merged through public pull requests with recorded provenance, and you can claim the publisher page for a contribution you maintain through the Publisher Studio.

The command mapping table is the audit trail for covered commands and catalog default floors. Pair it with the reviewed rule and permission counts, the per-tool state mapping, and the exact source tree linked from View exact source at the reviewed commit. Guard records enforcement decisions with evidence locally, so what ships matches what you reviewed.