dialectforge avatar

FlowState Hosted

dialectforge/flowstate

Hosted shared memory for AI apps: project decisions, to-dos and learnings. Beta.

GitHub stars
22
tools
16
transport
HTTP
last updated
Nov 7, 2026

Tools

16 tools

Public tool metadata for what this MCP can expose to an agent.

start_hereCall first. Project brief (size: quick / standard / deep; deep is the full context); lists projects when called without one

Call first. Project brief (size: quick / standard / deep; deep is the full context); lists projects when called without one

No parameter schema in public metadata yet.

log_workRecord a new decision, change, problem, learning or todo (replaces=, source=, suggested=)

Record a new decision, change, problem, learning or todo (replaces=, source=, suggested=)

No parameter schema in public metadata yet.

searchFind records by words (and by meaning, if set up); answer=true answers a plain question from your records with their ids; no query lists the newest records (since_hours)

Find records by words (and by meaning, if set up); answer=true answers a plain question from your records with their ids; no query lists the newest records (since_hours)

No parameter schema in public metadata yet.

manage_todoslist, next, update (done / cancelled), block / unblock; add for subtasks, blockers and due dates; claim / renew / release / handoff so several agents don't do the same todo

list, next, update (done / cancelled), block / unblock; add for subtasks, blockers and due dates; claim / renew / release / handoff so several agents don't do the same todo

No parameter schema in public metadata yet.

manage_problemslist, tree, add_attempt, end_attempt, solve

list, tree, add_attempt, end_attempt, solve

No parameter schema in public metadata yet.

manage_reviewThe review queue and review mode: list (one line per item; item_id for one in full), get_mode; walk (when you ask to see what's waiting: you decide each item in a box, or you get the links); approve, reject, set_mode only when you ask

The review queue and review mode: list (one line per item; item_id for one in full), get_mode; walk (when you ask to see what's waiting: you decide each item in a box, or you get the links); approve, reject, set_mode only when you ask

No parameter schema in public metadata yet.

manage_handoffsLeave / list / pick up "where I was, next step" notes

Leave / list / pick up "where I was, next step" notes

No parameter schema in public metadata yet.

manage_rulesA project's hard rules (one an AI adds or removes waits in the review queue until you approve it yourself)

A project's hard rules (one an AI adds or removes waits in the review queue until you approve it yourself)

No parameter schema in public metadata yet.

manage_linksLink projects, shared components, records and URLs

Link projects, shared components, records and URLs

No parameter schema in public metadata yet.

manage_historySee edits; undo the last change to a record; action="who": who did what (app, model, machine), with filters

See edits; undo the last change to a record; action="who": who did what (app, model, machine), with filters

No parameter schema in public metadata yet.

manage_projectsProjects and components: list, create, update, list_components, add_component, update_component; delete / delete_component only when you ask (undoable; with approvals on they wait for you)

Projects and components: list, create, update, list_components, add_component, update_component; delete / delete_component only when you ask (undoable; with approvals on they wait for you)

No parameter schema in public metadata yet.

manage_memoryUpkeep: cleanup suggestions and memory imports (to the review queue), stale facts, mark checked, set source; delete one record when you ask (undoable; with approvals on it waits for you)

Upkeep: cleanup suggestions and memory imports (to the review queue), stale facts, mark checked, set source; delete one record when you ask (undoable; with approvals on it waits for you)

No parameter schema in public metadata yet.

show_review_cardOnly in apps that draw cards and are on your card list. Shows what's waiting (one item, or up to 5, oldest first) as cards you tap. Read-only

Only in apps that draw cards and are on your card list. Shows what's waiting (one item, or up to 5, oldest first) as cards you tap. Read-only

No parameter schema in public metadata yet.

show_conflict_cardSame apps. Shows a disagreement as a card: Keep A, Keep B or Keep both. Read-only

Same apps. Shows a disagreement as a card: Keep A, Keep B or Keep both. Read-only

No parameter schema in public metadata yet.

resolve_review_cardSame apps. Hidden from the AI: the card calls it when you tap, and it refuses chat text

Same apps. Hidden from the AI: the card calls it when you tap, and it refuses chat text

No parameter schema in public metadata yet.

resolve_conflict_cardSame apps. Hidden from the AI: the card calls it when you tap, and it refuses chat text

Same apps. Hidden from the AI: the card calls it when you tap, and it refuses chat text

No parameter schema in public metadata yet.

Sponsors

Readme

FlowState

mcptry

A shared project memory for your AI apps. Free, open source, and stored on your own machine.

Don't want to run a server? Try FlowState Hosted. The same shared memory, hosted for you at flowstatemcp.com/hosted. Add one URL (https://hosted.flowstatemcp.com/mcp) to Claude, ChatGPT, Cursor or VS Code and sign in. No install, no Python, no tunnel. Your data is encrypted at rest and backed up, and you can export or erase it any time. Beta: 6 months free, then $6/mo for beta members ($12/mo regular). No card needed to start. 10 beta spots.

Prefer to keep everything on your own machine? Keep reading: local FlowState is free and MIT forever.


View the full README on GitHub

Details

Repository
github.com/dialectforge/flowstate
Website
flowstatemcp.com/hosted
Category
AI & LLM Tools
Transport
HTTP
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1tailucanh avataroffloadtailucanh/offload-mcp-serverHand heavy read-only work to a background agent CLI (Antigravity) and read back a short report.21stars
2muvon avatarOctobrainmuvon/octobrainPersistent memory for AI assistants with semantic search and knowledge graph relationships.20stars
3risingwavelabs avatarRisingWaverisingwavelabs/risingwave-mcpQuery, inspect and operate RisingWave, the PostgreSQL-compatible streaming database, from an agent.20stars
4e18e avatare18ee18e/mcpThe official e18e MCP server keeping your agent in check from installing bloated dependencies.0stars
5aishwaryshrivastav avatarVibe Test — Browser Testing Agentaishwaryshrivastav/vibe-testingCode-aware browser testing agent — 14 Playwright tools for AI code editors via MCP18stars
6abhigyan-shekhar avatarWaggle Mcpabhigyan-shekhar/waggle-mcpPersistent graph-backed conversational memory for AI agents.16stars