Documentation

The tela MCP server

Last updated June 27, 2026

tela ships a built-in Model Context Protocol server, so AI agents are first-class users of your wiki — they read, search, and write the same markdown your team does. This page is the public reference for connecting to it.

Endpoint

URL: https://telawiki.com/api/mcp
Transport: Streamable HTTP (the current MCP transport; SSE is not used).
Auth: OAuth 2.1 with PKCE (via WorkOS AuthKit), or a Personal Access Token as a bearer header.

Connecting

Claude

In Claude, add tela as a custom connector and point it at the endpoint URL above. Claude runs the OAuth flow — you sign in to tela and consent, and the tools become available in chat. No manual token handling.

ChatGPT

In ChatGPT's connector / Developer Mode settings, add a connector with the endpoint URL above and complete the OAuth sign-in. tela also exposes the search + fetch pair used by Deep Research.

Any MCP client (npm proxy)

For stdio-based hosts, the published tela-mcp package is a thin proxy that forwards stdio to the HTTP endpoint with your token:

{
  "mcpServers": {
    "tela": {
      "command": "npx",
      "args": ["-y", "tela-mcp"],
      "env": {
        "TELA_BASE_URL": "https://telawiki.com",
        "TELA_API_KEY": "<your personal access token>"
      }
    }
  }
}

Modern hosts that speak Streamable HTTP can skip the proxy and connect to /api/mcp directly.

Install

One-click

Add the HTTP endpoint to an editor in one click — OAuth handles sign-in on first use, so no token goes in the link:

Add to Cursor Add to VS Code

Per-client setup

HTTP-transport hosts connect to the endpoint directly and sign in via OAuth; stdio-only hosts use the tela-mcp proxy with a PAT (TELA_BASE_URL + TELA_API_KEY).

Claude Code (CLI, HTTP)

claude mcp add --transport http tela https://telawiki.com/api/mcp

Cursor (HTTP)

Use the button above, or add to ~/.cursor/mcp.json:

{ "mcpServers": { "tela": { "url": "https://telawiki.com/api/mcp" } } }

VS Code (HTTP)

Use the button above, or from the command line:

code --add-mcp '{"name":"tela","type":"http","url":"https://telawiki.com/api/mcp"}'

ChatGPT / Claude.ai (OAuth connector)

Add a custom connector, paste the URL, and complete the sign-in:

https://telawiki.com/api/mcp

Claude Desktop (stdio proxy)

In claude_desktop_config.json:

{
  "mcpServers": {
    "tela": {
      "command": "npx",
      "args": ["-y", "tela-mcp"],
      "env": {
        "TELA_BASE_URL": "https://telawiki.com",
        "TELA_API_KEY": "<your personal access token>"
      }
    }
  }
}

Windsurf (stdio proxy)

In ~/.codeium/windsurf/mcp_config.json, using the same mcpServers shape as Claude Desktop above.

Codex (stdio proxy)

In ~/.codex/config.toml:

[mcp_servers.tela]
command = "npx"
args = ["-y", "tela-mcp"]
env = { TELA_BASE_URL = "https://telawiki.com", TELA_API_KEY = "<your personal access token>" }

A machine-discovery manifest is published at /.well-known/mcp.json.

Tools

Thirty-nine tools, grouped by what they touch, with read and write cleanly separated. Every tool carries a human-readable title and read/write annotations; writes are scoped by your token's permissions. The knowledge tools help an agent keep the wiki connected — surfacing related pages, suggesting links, and flagging overlap — and the Atlas tools let an agent kick off and check a documentation run.

Read

list_spacesList the spaces you can access.
get_spaceRead a space and its metadata.
list_pagesList pages in a space, as a tree.
get_pageRead a page (canonical markdown).
list_backlinksPages that link to a given page.
read_chunkRead a specific section of a page.
searchKeyword full-text search across pages (no embedder needed).
researchSemantic, answer-oriented retrieval with cited sources.
fetchFetch a document by id (Deep Research).

Write

create_spaceCreate a new space.
update_spaceRename or edit a space.
delete_spaceDelete a space.
create_pageCreate a page from markdown.
update_pageEdit a page body or title.
patch_pageApply a section-scoped edit to a page.
move_pageRe-parent or reorder a page.
delete_pageDelete a page.
add_commentComment on a page.
submit_feedbackSend feedback to the maintainers.

Knowledge

related_pagesPages semantically related to one (see-also).
suggest_linksSuggest links from draft text to existing pages.
find_overlapsFind pages with overlapping or duplicate content.
knowledge_gapsTop questions the docs couldn’t answer (admin).

Atlas

atlas_list_projectsList Atlas projects you can manage or view.
atlas_runTrigger an Atlas run — generate or refresh a source.
atlas_run_statusCheck a run — stage, status, and coverage.

Sheets

sheet_authoring_guideThe guide for authoring tela spreadsheets — the table format, formulas, and styling.

Decks

preview_deckRender a deck to preview its slides.
lint_deckCheck deck markdown before presenting.
deck_authoring_guideThe guide for authoring tela decks.
generate_deck_imageGenerate an image for a slide.
treat_deck_imageProcess and optimize a slide image.

Attachments

list_attachmentsList a page's attachments.
request_attachment_uploadStart an upload and get an upload URL.
confirm_attachment_uploadFinalize an attachment upload.
upload_attachmentUpload a file attachment to a page.
delete_attachmentRemove an attachment.

Sharing

share_pageCreate a public share link for a page.
revoke_shareRevoke a page’s share link.
list_sharesList active share links.

Resources

tela exposes pages and spaces as MCP resource templates, so agents can reference them by URI:

tela://page/{id} — a page by id.
tela://space/{id} — a space by id.

Interactive widgets

On hosts that support MCP Apps / interactive UI, tela returns two embedded widgets — a page reader and search-results cards — so results render as interactive components instead of raw text.

Permissions & safety

Agent tool calls run with your account's permissions — an agent can only touch what you can.
Write tools are gated separately from read tools; read-only connections never mutate content.
Page bodies are canonical markdown — what an agent writes is exactly what your team sees.
See the privacy policy for what is collected and shared.

Limitations

Semantic retrieval needs an embedder. research (and the semantic side of retrieval) returns 503 if the instance has no embedding model configured. Keyword search always works.
Large pages are capped. get_page and fetch truncate bodies beyond ~80k characters and set truncated: true; read specific sections with research + read_chunk.
Writes need editor permission. Create/update/delete tools require editor access on the target space; a read-scoped token or a viewer account can't write.

Troubleshooting

Connect fails / "couldn't register": The host couldn't complete OAuth. Re-add the connector with the exact URL https://telawiki.com/api/mcp, then sign in and consent when the tela login screen appears.
401 / tools don't appear: The token is missing or invalid. For the OAuth flow, reconnect; for the npm proxy, check TELA_API_KEY is a current Personal Access Token.
Tool returns 503 rag_disabled: Semantic retrieval isn't configured on this instance — use keyword search instead.
A page comes back truncated: Expected for very large pages (truncated: true). Use research to find the relevant section, then read_chunk.
Write tool returns a permission error: Your account or token lacks editor access to that space.

Still stuck? Email tela@telawiki.com — the source is on GitHub.

Source, support & security

tela is open-source at github.com/zcag/tela; the MCP proxy is tela-mcp on npm. Questions and support: tela@telawiki.com. Report security vulnerabilities privately to tela@telawiki.com — please don't open a public issue for security reports.