MCP servers · cloudcorprecords

agenttrio: bounded planner, coder and reviewer agent workflows over MCP

An MCP server and command-line tool that runs bounded planner, coder and read-only reviewer workflows on a local Ollama backend, with a verification gate.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

agenttrio runs a task through three roles: a planner, a coder and a separate read-only reviewer, using a local Ollama backend. A run is reported as verified only when a host-enforced gate passes: the planner and coder stay within their budgets, at least one required named check runs and every required check passes, and the reviewer returns a JSON approval. If the gate fails, the coder, checks and reviewer cycle repeats up to max_cycles, and the report names the failed condition. Model turns, cycles, tool calls and context size are all capped by the operator config.

It suits projects where a coding task should pass configured checks and a separate review before it counts as verified. It runs as a command-line tool or as a sequential stdio MCP server exposing three tools: flow_status, flow_run and flow_check.

Running it requires an operator-reviewed TOML config passed explicitly with --config, because workspace config files are not auto-loaded; without a resolvable config, every command fails with an error. The default mode is read-only, and run and check require --trusted to allow project edits and named checks. Non-loopback Ollama endpoints are refused unless ollama.allow_remote is set. Reports print as JSON, and exit codes distinguish success, runtime failure and usage errors.

Limitations and requirements

Requires a running Ollama instance with a tool-capable model pulled locally. Requires an operator-reviewed config file; every command fails without one. run and check require --trusted to edit project files and execute named checks. Non-loopback Ollama endpoints are refused unless ollama.allow_remote is set. The MCP server is deliberately sequential.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    io.github.CloudCorpRecords/agenttrio

    Bounded planner-coder-reviewer workflows: status, verified run, and configured checks.

    v0.1.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 18 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 18 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 18 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 18 Nov 2026
agenttrio: bounded planner, coder and reviewer agent workflows over MCP | AI Gate Discover