
METODIC MCP server
Which servers in the official MCP registry are METODIC's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-17
- Registry nameio.metodic/metodicverified in the MCP registry
The registry name sits under metodic.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-17
- Tools20
- Server calls itselfMetodic
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-17 the server answered initialize and tools/list without a sign-in. First answer in 279 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 4 of the 7 days it takes to judge reliability.
Once connected
- For "generate a timed meeting agenda from a short brief", the likely first call is design_session.
- add_debrief change data without a sign-in: anyone with the address can call them.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer341 ms
- Space in an agent's context≈ 5,723 tokensthe definitions of all its tools (20), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 20 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · generate a timed meeting agenda from a short brief
- not sure · create printable worksheets and handouts for each workshop activity
- not sure · build presentation slides and a facilitator script for a session
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
- Tools that change data, on a server that answers without a sign-in: add_debrief
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_frameworksBrowse Metodic's learning and facilitation frameworks (Design Thinking, Liberating Structures, 4C/ID, PreMortem and more) with what each is best for and when to use it. Use it to ground a session design in a real methodology rather than a…
find_session_formatSTART HERE when someone describes a PROBLEM or CHALLENGE ('our leadership team works in silos', 'nobody speaks up in retros', 'we need to align on strategy') and wants a session for it. Returns proven, ready-made session formats from…
answer_from_libraryThe answer format for anything the user could pick up and use. ALWAYS use this — not generate_document, not prose, not a web search — for a question about WHAT TO USE OR READ — 'which energizer for a flat afternoon group', 'what learning…
search_articlesSearch Metodic's own published articles on facilitation, workshop design and learning. Use this BEFORE reaching for the open web whenever the user asks for sources, background, reading or inspiration: Metodic has its own writing on these…
search_methodsSearch Metodic's library of PROVEN facilitation methods — hundreds of real, tested formats with timing, step-by-step instructions, facilitator tips and materials (plus any the user saved themselves). ALWAYS use this before suggesting an…
design_sessionTurn the conversation into a REAL session in the user's Metodic account: a timed agenda built from the method library, saved and ready to run, edit, share and export. Returns a session_id immediately and the Metodic card fills itself in…
design_statusCheck whether a session started with design_session is ready. While generating it returns a wait instruction; when ready it returns the BRANDED HTML SESSION BRIEF — render it as an artifact. Free (no credits).
refine_sessionModify an existing session's agenda IN PLACE without leaving the chat: retime, rename, move, remove or update activities, or add new ones. Put EVERY change the user asked for in ONE call — a second call paints a second full session brief…
get_sessionREAD a session so YOU know what is in it before answering a follow-up — this returns text for you, not something the user sees. To SHOW the session to the user, call session_one_pager instead. Gives every activity's agenda slot, method…
session_one_pagerReturn a complete, self-contained, Metodic-BRANDED HTML one-pager of a session (logo, brand colours, agenda table, activity cards). RENDER THE RETURNED HTML AS AN ARTIFACT so the user sees the branded document. Use for the FULL session…
generate_documentNOT for a list of sources, methods, formats or reading — that is answer_from_library, which draws on Metodic's own library and saves the result to the session. Use this only for a WRITTEN DOCUMENT with its own audience: a pre-read, a…
list_my_sessionsList the user's recent Metodic sessions with links.
share_sessionCreate a shareable link to a session so someone else can see it WITHOUT a Metodic account: a client or sponsor who has to approve the programme, a co-facilitator, or the participants. Optionally writes a client-facing brief first…
get_creditsShow the user's available Metodic credits (the balance that generation tools spend — for team members this is the team's shared balance). Call when the user asks about credits, cost, or whether they can afford a generation.
add_debriefSave a post-session DEBRIEF onto the session in Metodic: how it went, what worked, what to improve, follow-ups. Call after the user has run their workshop and tells you how it went (or after a debrief conversation) — synthesize first…
generate_worksheetGenerate the A4 PARTICIPANT WORKSHEET for ONE activity — the sheet each participant fills in on their own, at the table. NOT the big sheet on the wall: if the user says canvas, wall canvas, poster, brownpaper, large format, A1, A0, matrix…
generate_canvasTHE TOOL FOR ANY CANVAS. Generate the large-format WALL CANVAS for ONE activity using Metodic's real canvas generator, and return it as a branded document in the chat (also saved to the session, and replayable 1:1 to a Miro board). This…
generate_handoutGenerate a participant HANDOUT or reference material for ONE activity using Metodic's real generator, and return it as a branded HTML artifact in the chat (also saved to the session). Unlike a worksheet (which participants fill in), a…
generate_slidesGenerate the session's SLIDE DECK with Metodic's real generator — the same facilitation deck the Metodic app makes: an opening, the day's journey with real times, per activity a chapter, the task (steps, who with, what you make, what you…
generate_cardsGenerate a METHOD CARD DECK for the session using Metodic's real generator, and shown in the chat as Metodic's paper cards (category post-it colours, icon on the front, steps and a tip on the back; tap a card to turn it). Also saved to…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"metodic": {
"type": "http",
"url": "https://www.metodic.io/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http metodic https://www.metodic.io/mcpclaude.ai, ChatGPT and other clients: add https://www.metodic.io/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.