Docs / Claude Code & Codex

Claude Code & Codex

How Flanner connects to your coding agent, and the MCP tools it exposes.

What init registers, and where

Three agents, three different files. flanner init registers the server in Claude Desktop's config, writes a project-scoped .mcp.json that Claude Code reads, and adds managed blocks to CLAUDE.md and AGENTS.md. Codex reads AGENTS.md but registers MCP servers in its own file, which flanner does not edit. Add this to ~/.codex/config.toml:

[mcp_servers.flanner]
command = "flanner-mcp"

flanner status shows one row per agent, each checked where that agent actually looks. Narrow what init registers with --setup codex, or turn it off with --skip-claude.

flanner claude-info # Check integration status

Manual registration

If needed, you can register, update or remove it by hand. flanner setup re-runs everything init would have done.

flanner register

flanner register --force # Force update

flanner unregister # Unregister

Guidance and the guard hook

flanner init sets up two things so your agent saves plans through Flanner without being reminded. Both work with Claude Code and Codex.

Guidance the agent reads

flanner init writes a managed block into CLAUDE.md and AGENTS.md, which Claude Code and Codex read every session, and installs a flanner-plan skill. Together they tell the agent to save plans through the MCP tools.

A guard hook as backstop

A guard-write PreToolUse hook denies any raw write into the plan directory and points the agent back to create_plan_file_tool. It fails open and never blocks writes elsewhere.

MCP tools the agent calls

create_plan_file_toolCreate a plan file (adds the YAML header, records v1)

update_plan_file_toolRevise a plan and record a new version

get_plan_file_toolRead a plan file

list_plan_files_toolList plan files in a project

get_plan_history_toolGet the full version history of a plan

get_plan_freshness_toolCheck a plan's freshness status and evidence before trusting it

link_plan_to_linear_toolLink a plan to a Linear issue

link_plan_to_jira_toolLink a plan to a Jira issue

get_plan_configConfirm the plan directory and header format

get_plan_assurance_toolWhether a plan is safe to implement, and exactly what it is if not

initialize_project_toolAdopt a repository so its plan documents are tracked

create_project_toolCreate a project with git integration

list_projectsEvery project and its configuration

configure_project_toolChange a project's settings

delete_project_toolDelete a project and its plan files from the database

propose_plan_revision_toolOffer a plan version for review

record_plan_review_decision_toolRecord a decision against a proposal

get_plan_workflow_status_toolA plan's open proposals and its accepted baseline

configure_jira_toolSet up the Jira connection

get_jira_config_toolShow the Jira connection

get_jira_links_toolWhich Jira issues one plan is linked to

list_jira_links_toolEvery Jira link in a project

unlink_jira_issue_toolRemove a Jira link

configure_linear_toolSet up the Linear connection

get_linear_config_toolShow the Linear connection

get_linear_links_toolWhich Linear issues one plan is linked to

list_linear_links_toolEvery Linear link in a project

unlink_linear_issue_toolRemove a Linear link

memory_rememberSave one durable fact for later sessions

memory_recallSearch memory, with the reason each result matched

memory_getRead one memory in full

memory_listBrowse memories in a project

memory_supersedeCorrect a memory by replacing it

memory_forgetStop recalling a memory

memory_considerPropose a memory for the person to approve

memory_pendingSuggestions still waiting on a decision

memory_decideApprove or reject a suggestion

memory_policyWhat this project will let be remembered

memory_attachAttach a file to a memory as evidence

memory_detachRemove an attachment

memory_shareShare one memory with the team, when asked to

memory_withdrawAsk peers to stop recalling a shared memory