Archivist AI MCP Server
Enables Notion AI to access and manage TTRPG campaign data from Archivist AI, including characters, sessions, locations, factions, items, and more.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Archivist AI MCP Serverwhat are the active quests in my campaign?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Archivist AI MCP Server
The official Model Context Protocol (MCP) server for Archivist AI -- a TTRPG campaign memory platform for game masters and players.
Registry metadata lives in server.json. Publishing to the official MCP Registry is automated on version tags via .github/workflows/publish-mcp.yml (git tag v1.0.0 && git push origin v1.0.0).
Connect AI assistants like Claude, ChatGPT, Cursor, Notion, and Windsurf directly to your campaign data: characters, sessions, locations, factions, items, quests, journals, and more.
Quick Start
MCP Server URL: https://mcp.myarchivist.ai/mcp
Claude Desktop requires the mcp-remote proxy (Node.js must be installed).
Add to your claude_desktop_config.json (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"archivist-ai": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.myarchivist.ai/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer YOUR_API_KEY"
}
}
}
}Replace YOUR_API_KEY with your Archivist AI API key from app.myarchivist.ai. Restart Claude Desktop after saving.
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"archivist-ai": {
"url": "https://mcp.myarchivist.ai/mcp"
}
}
}Add to your MCP configuration:
{
"mcpServers": {
"archivist-ai": {
"serverUrl": "https://mcp.myarchivist.ai/mcp"
}
}
}Archivist AI is available as a ChatGPT plugin. Search for "Archivist AI" in the ChatGPT plugin store.
Related MCP server: MCP-Kanka
Available Tools
Read tools are non-destructive and idempotent. Write tools follow standard REST semantics — deletes are destructive and idempotent; PATCH is non-idempotent; PUT is idempotent. Every read tool that returns text-carrying descriptions (Character, Faction, Location, Item, Moment, Beat, Session, Journal) accepts an optional with_links parameter — see Wikilinks below for why you almost always want to pass with_links: true before editing.
Campaign delete, session delete, product-view-only endpoints (beat reorder/batch-edit, campaign settings, cast/member management), and multipart recording uploads are intentionally not exposed.
OAuth scopes and write access
OAuth clients that connect via https://app.myarchivist.ai request scopes at authorization time. Every write tool (create/update/delete + image generation and upload) additionally requires the agent_write scope on the caller's token.
The MCP mirrors the API's enforcement in tools/list: agent clients without agent_write see only the read tools, and receive a "tool not found" JSON-RPC error if they attempt to call a write tool anyway. API-key credentials and non-agent OAuth clients bypass this filter — the API is the authoritative gate for them and all tools remain visible.
Existing OAuth clients that connected before agent_write was advertised need to re-authorize to receive a token with the new scope.
Campaigns
Tool | Description |
| List your campaigns. Returns a paginated list. |
| Get a specific campaign by ID. |
| Get statistics for a campaign: character count, session count, and more. |
| Create a new campaign. Subject to the account's subscription-tier campaign limit. |
| Partially update campaign metadata (title, description, tones, public/mature flags). |
Sessions
Tool | Description |
| List game sessions. Filter by session type or public-only. |
| Get a session by ID. Optionally include related beats and moments. |
| Get cast analysis: talk-share breakdown and core session metrics. |
| Get the cleaned transcript for a game session, including utterances, full text, and aggregate stats. |
| Get the generated session handout for a game session, including summary, outlines, spotlights, and notable moments. |
| Partial update (title, session_date, summary, image). Explicit-link contract for wikilinks. |
| Full update (PUT). Explicit-link contract for wikilinks. |
Story Structure
Tool | Description |
| List beats ordered by index. Beats represent story moments (major, minor, step). |
| Get a specific beat by ID. |
| Create a beat. Explicit-link contract for wikilinks. |
| Partially update a beat. |
| Delete a beat (child beats have parent_id cleared). |
| List moments in a campaign or session. Moments capture memorable quotes and events. |
| Get a specific moment by ID. |
| Create a moment attached to a session. Explicit-link contract for wikilinks. |
| Partially update a moment. |
| Delete a moment. |
World Building
Tool | Description |
| List characters in a campaign. Filter by name, type (PC/NPC), or approval status. |
| Get a character by ID including aliases, backstory, and speaker linkage. |
| Create a character. Description/backstory wikilinks auto-resolve. |
| Partially update a character. Read with |
| Delete a character. API unbrackets all inbound |
| List factions. Factions represent guilds, organisations, or other groups. |
| Get a specific faction by ID. |
| Create a faction. Description wikilinks auto-resolve. |
| Partially update a faction. Read with |
| Delete a faction. |
| List locations. Locations can be nested (cities, taverns, dungeons, etc.). |
| Get a specific location by ID. |
| Create a location. Description wikilinks auto-resolve. |
| Partially update a location. Read with |
| Delete a location (child locations have parent_id cleared). |
| List items. Items include weapons, armour, artefacts, and other notable objects. |
| Get a specific item by ID. |
| Create an item. Description wikilinks auto-resolve. |
| Partially update an item. Read with |
| Delete an item. |
Quests
Tool | Description |
| List quests with pagination. Filter by status or category. |
| Get a fully expanded quest: objectives, progress log, related entities, session provenance. |
| Create a quest entry. Quests do not participate in the wikilinks system. |
| Partially update a quest. Lists you send replace their corresponding lists on the record. |
| Delete a quest and its objectives / progress entries / related refs. |
Journals
Tool | Description |
| List journal entries. Content omitted from list; use get_journal for full content. |
| Get a journal entry by ID including full content and permission level. |
| Create a journal entry. Returns |
| Update a journal entry (PUT). Returns |
| Delete a journal entry (embeddings are best-effort deleted). |
| List journal folders ordered by path and position for tree rendering. |
| Get a specific journal folder by ID. |
| Create a journal folder (owners/admins only; path must be unique per campaign). |
| Update a journal folder (PUT). |
| Delete a folder; entries move to the campaign root. |
Relationships
Tool | Description |
| List links between entities. Filter by source/target entity and relationship alias. |
| Create a Link row between two entities (upserts if |
| Update an existing link's alias. |
| Delete a single Link row (does not rewrite the source's text). |
| Trigger campaign-wide link maintenance (add/remove/update) via webhook — requires an active subscription tier. |
Images
Tool | Description |
| Return the calling account's image quota for a campaign: |
| Server-side AI generation for |
| Step 1 of direct upload: reserve an |
| Step 2 of direct upload: validate the uploaded object, run NSFW moderation, and (when |
| Remove an image. Provide |
Wikilinks
Descriptions, summaries, moment content, and journal bodies in Archivist AI can contain [[Target Name|Optional Alias]] markup that resolves to real records. Every write tool that touches a text field carrying wikilinks has to follow a small protocol to avoid destroying existing links.
The one rule you must follow
Always read with with_links: true before writing. Every Get/List tool for Character, Faction, Location, Item, Moment, Beat, Session, and Journal accepts this parameter. The API defaults to stripping wikilinks so that read consumers get clean prose, which means a naive read/modify/write cycle will erase every [[…]] on the source record. Passing with_links: true returns the text with brackets intact so you can preserve them on write.
Per-record contract
Record type | Contract |
Character, Faction, Location, Item, Character.backstory | Auto-resolve. On write, the API extracts |
GameSession, Beat, Moment | Explicit-link only. The API strips |
Journal | Rendering-only. Stored |
Quest | No wikilinks. Quest text fields are stored verbatim. Relationships are modelled via the |
Delete (any record) | The API automatically unbrackets all |
Renaming and repointing
Rename an alias: edit inside the brackets.
[[Alice|Al]]→[[Alice|Ali]].Repoint at a different target: change the visible target name.
[[Alice]]→[[Alicia]].Remove a link: unbracket the alias in the text (auto-resolve) or call
delete_link(explicit).Campaign-wide rename or repoint for a compendium target: use
bulk_link_maintenancewithoperation: "update",new_alias, and/ornew_target_id. The API rewrites every referring text field in a background webhook and returns atask_id.
Images
Entity images can be added to Characters, Factions, Locations, Items, Moments, Sessions, and the Campaign itself. Two flows are supported:
Server-side AI generation
Call generate_image with a campaign_id, a type (character, faction, location, item, or world), and optionally an entity_id (defaults to the campaign for type=world) and free-form user_input. The API rewrites the entity's stored description into a visual prompt, calls the configured provider, and returns a public URL.
Two things worth calling out:
The generated image is not automatically attached — set
imageon the entity via the matching update tool (e.g.update_character,update_faction) if you want to persist it on the record.Generation consumes the account's per-cycle image quota. Call
get_image_usagefirst if you need to reason about headroom, tier limits, or the current billing window. AI features are disabled on archived campaigns.
Direct upload (two-step)
For images the user already has on disk or in memory, use the presigned-URL flow:
Call
init_image_uploadwithcampaign_id,entity_type,entity_id,file_name, andcontent_type(must beimage/*). You receiveobject_key,upload_url,public_url, andexpires_in_seconds.Your client (or a human collaborator) issues an HTTP
PUTtoupload_urlwith the raw image bytes and the sameContent-Typeheader before the URL expires. This step happens outside the MCP transport.Call
complete_image_uploadwithobject_key,entity_type,entity_id, andattach(defaults totrue). The API validates the upload, runs NSFW moderation, and — whenattachis true — sets the entity'simagefield to the moderatedpublic_url.
Agents that cannot make arbitrary HTTP PUTs should prefer generate_image or hand the PUT step off to a human between step 1 and step 3.
Removal
delete_entity_image removes an image within a campaign in one of two modes:
By entity: pass
entity_type+entity_id. The API detaches the image from the record AND deletes the underlying object.By URL: pass a managed
image_url(e.g. from a previousinit_image_uploadresponse). Deletes just the object.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Astrotomic/mcp.myarchivist.ai'
If you have feedback or need assistance with the MCP directory API, please join our Discord server