FlowState Hosted is answering right now. Last checked moments ago. It exposes 16 tools. Last commit 7 Nov 2026.
Hosted shared memory for AI apps: project decisions, to-dos and learnings. Beta.
Uptime history
43 hours of history · worst hour 0%
43 hours agonow
100.0%
Uptime 24h
92 of 92 checks
16
Tools
read from the server
367 ms
Response time
average over 24h
22
Stars
last commit 7 Nov 2026
What the code does
We read the source, 20 h ago · tools taken from the live server · rules 995398eba69f
Capabilities
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
Runs an external command
mcp-server/flowstate/cloudflared_check.py:28, mcp-server/flowstate/git_capture.py:56, mcp-server/flowstate/offsite.py:115 и ещё 3
r = subprocess.run([exe, "--version"], capture_output=True, text=True,
Dumps the whole environment
mcp-server/flowstate/selfupdate.py:125
env = dict(os.environ, GIT_TERMINAL_PROMPT="0", LC_ALL="C", LANG="C")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
run in your terminal
claude mcp add flowstate-hosted --transport http https://hosted.flowstatemcp.com/mcpSettings → Connectors → Add custom connector, then paste this address
https://hosted.flowstatemcp.com/mcp~/.codex/config.toml
[mcp_servers.flowstate-hosted]
url = "https://hosted.flowstatemcp.com/mcp".cursor/mcp.json
{
"mcpServers": {
"flowstate-hosted": {
"url": "https://hosted.flowstatemcp.com/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"flowstate-hosted": {
"type": "http",
"url": "https://hosted.flowstatemcp.com/mcp"
}
}
}Available tools 16
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
manage
manage_handoffs
Notes from one AI to the next. leave: before you end, if you stop mid-task, save where_i_was and next_step; the next start_here shows it after the hard rules. pickup: once you continue from a note, mark it so it stops showing. list: open notes. Not a session summary and not a todo. Adds or marks notes; never deletes. Returns the note or {notes}.
manage_history
The edit trail of records. list: edits with old and new values. undo: take back a record's last edit, a record you created (if nothing refers to it), or a delete with everything removed with it (a deleted project: its old name and id); rows changed since are skipped and listed. who: who did what (app, model, machine), filtered and paged. metrics: usage counts only (brief sizes, how often search and ask returned records). Logged changes (kind=change): find them with search. Reads: list, who, metrics. list and undo require project. Returns {history}, the undo result, or {rows, page}.
manage_links
Connect things across projects. add: a project uses a shared component (link_type=uses, target_project, target_component), depends on a project, two components are the same, records relate, or a record gets a URL (e.g. an issue). Then a change or decision logged on the shared component (log_work component=<name>) gives each linked project an update todo and a 'changed since' line; FlowState never edits other projects. remove: by link_id or the add fields; kept as removed (manage_history undo, record_type=link). flag_conflict: two records disagree (topic, evidence); the user keeps one. list: read-only. Requires project. Returns the link, the card, or {links}.
manage_memory
Memory upkeep. cleanup: queue likely duplicate, stale and misfiled records. import: a memory export or edited FlowState markdown into review. stale: facts unchecked for 60+ days, and records flagged possibly stale. files_changed: paths you changed; flags records whose file evidence names them. mark_checked: you re-checked one (clears the flag). set_source: correct an origin (user_stated waits for the user). set_aside: no longer applies but kept (needs reason; out of brief and search; restore_set_aside or undo). delete: only when the user asks; undo restores it; with approvals on it waits for the user's approve (manage_review). Requires project. Returns counts and ids.
manage_methods
Documented reusable procedures of a project (deploy, test, a code convention), with ordered steps. create, list (read), update (steps replaces the whole list; undo with manage_history), delete (undo restores it; with approvals on it waits for the user; refused for HTTP app keys and remote apps). A one-off choice is log_work kind=decision; a lesson is kind=learning. Requires project. Returns method rows.
manage_problems
Work on a project's existing problems (bugs, blockers). list: open problems. tree: one problem with every attempt and its solution. add_attempt: record a try. end_attempt: how a try ended. solve: close it with what fixed it (manage_history undo reopens it). Call add_attempt or solve right after a fix, and again before you end or hand back. Open a new problem with log_work kind=problem. Reads: list, tree. Writes need project. Returns problem rows, the tree, or the saved attempt or solution.
manage_projects
Projects and their components (named parts of a project). list: projects (by status). create: only when the user asks; names are unique. update: rename, describe, or set status (archived retires it). list_components / add_component / update_component: the same for components (deprecated retires one). delete / delete_component: only when the user asks. Deletes it with its child records after a safety copy; the answer gives the undo call. If the user turned approvals on it waits for their own approve instead (manage_review lists it; tell them the answer's next line). Reads: list, list_components. Returns project or component rows, or what was deleted.
manage_review
The user's review queue and mode: summaries, suggestions, imports, clean-ups, deletes, conflicts. list (a line each; item_id: one in full), get_mode: read-only. walk: when the user asks what's waiting (boxes or links). approve: make it a record (edit / move_to first), delete (confirm_name), confirm a conflict (keep=a|b|both). set_mode: which new records wait. approve, reject, set_mode: ONLY call this when the user has explicitly told you, in this chat; quote them in user_request; never approve your own suggestions or change the mode to get your own writes saved. Hosted: approve/reject are refused for every AI; share the review page link. Returns {items, total}, the mode, or the result.
manage_rules
A project's hard rules: short never/always rules from the user, shown first in every brief and never cut. add: when the user states one (one sentence, max 300 chars; 25 rules, 2,000 chars in total); it waits in the review queue until the user approves it themselves (on their review page; no app can). list: active rules. remove: ONLY when the user asks in this chat; quote them in user_request; it waits like add; the rule is kept as removed. Preferences and lessons go in log_work. Requires project. Returns the rule or {rules}.
manage_sessions
Inspect FlowState's sessions. They open and close by themselves (closed after 2 hours idle or when the app quits, with a summary queued for review), so this is rarely needed. current, list, conversations: read. start: returns the automatic session. end: close one with a summary (not undoable). Decisions go in log_work. Returns session or conversation rows.
manage_skills
The connected app's own learned skills, checkpoints and metrics: how the AI works, not project facts (those go in log_work). learn: save a skill. list: a project's and global skills. confirm: one more session where it held (promoted after 3 at a 0.8 rate). save_state / get_state: a checkpoint. log_metric / list_metrics: scores. Reads: list, get_state, list_metrics; the rest only add rows or counts. Returns rows.
manage_todos
Todos. list; next: top unblocked (others' claims last). update: status, priority or title, when done and before you end. block / unblock: waits on todos or a problem. add: subtask, blocker or due date only (else log_work). claim before you start (fails if someone has it); renew; release or handoff (with a note). Returns rows.
manage_variables
Non-secret project settings: hosts, ports, endpoints, config. create, list (read), update (undo with manage_history), delete (undo restores it; with approvals on it waits for the user; refused for HTTP app keys and remote apps). Secrets are refused; is_secret only labels a value and does not hide it, so never store passwords, tokens or keys. Requires project. Returns variable rows.
log
log_work
Record one decision (a choice and why), change, problem, learning or todo. Call it right after each decision, change, fix or lesson, and before you end or hand back. To update todos or problems: manage_todos / manage_problems. Only adds. Review mode or suggested=true may queue it. A shared-component change alerts linked projects. A close decision gets a possible-conflict note; act on it. conflicts_with opens a disagreement card. Secrets are refused. Returns {logged, record, note} or {queued_for_review}.
search
search
Find stored todos, decisions, changes, learnings, problems and solutions. query: ranked matches. query + answer=true: a short quoted answer with record ids, or says FlowState has nothing. query="D12": decision 12 in full. No query: the newest records. Read-only. Overview: start_here. Returns {results, count} or {answer, sources}.
start
start_here
CALL THIS FIRST in every conversation about a project. Returns the brief as text: hard rules, a handoff note if any, review mode, possible conflicts, open todos (and claims) and problems, recent changes, decisions and learnings. No project: lists projects. Side effects: opens or reuses the automatic session, notes when you looked.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://hosted.flowstatemcp.com/mcp | streamable-http | answering | 339 ms | 0 min ago |
Alternatives to FlowState Hosted
same job, measured the same wayStele
by stele-ai
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
KLYPIX Shared Project Memory
by dahshanlabs
Shared project memory for Claude Code, Codex and Cursor: decisions, corrections, overlap warnings.
RepoMemory
by repomemory
Shared project memory for coding agents: decisions, lessons, guardrails and tasks per repository.
Robrain
by adelinamart
Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.
Mnema — Shared Brain for You and Your AI Agents
by theboringpeople
Self-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale
Beep
by getbeep
Shared memory for AIs. Share a project with anyone and their AI knows everything yours does.
Joxo
by joxo
One shared project for a team's coding agents: decisions, a task board and handoffs.
AiNecto
by ainecto
Shared project memory for people and AI agents: documents, ERD, diagrams, boards, design mockups.
FlowState Hosted — questions
Answers built from our own checks of this server.
What can FlowState Hosted do?
It exposes 16 tools, read directly from the server on our last check. Among them: log_work, manage_handoffs, manage_history, manage_links, manage_memory, manage_methods and 10 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is FlowState Hosted working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 367 ms. The bar chart above shows every period we have measured.
How do I connect FlowState Hosted?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does FlowState Hosted need an API key?
No. FlowState Hosted completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 16 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is FlowState Hosted?
It answers our handshake in 367 ms on average, which is faster than 37% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is FlowState Hosted open source?
The code is open source: it is published under the MIT licence, written in Python and 22 stars on GitHub. The licence covers the code in the repository, not the hosted service at hosted.flowstatemcp.com, which runs on its operator's own terms.