From dd46f971996888910630827bc438253ae51e7a40 Mon Sep 17 00:00:00 2001 From: Lukas Bindreiter Date: Wed, 18 Feb 2026 12:16:12 +0100 Subject: [PATCH 1/2] Document MCP server Oauth --- ai-assistance.mdx | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/ai-assistance.mdx b/ai-assistance.mdx index 2d6a5b7..3b66f24 100644 --- a/ai-assistance.mdx +++ b/ai-assistance.mdx @@ -20,21 +20,19 @@ The Tilebox MCP server at `https://mcp.tilebox.com/mcp` provides tools for: - Accessing and interacting with Tilebox datasets and workflows - Searching the Tilebox documentation -It requires authentication using a Tilebox API key. When configured, AI agents can query datasets, interact with workflows, and search the documentation for detailed context on specific topics. +It requires authentication via OAuth. When connecting, you'll be redirected to sign in with your Tilebox account and select a team to authorize the MCP server for. +When configured, AI agents can query datasets, interact with workflows, and search the documentation for detailed context on specific topics. ### Configuring the Tilebox MCP server To configure your AI tools to use the Tilebox MCP server, you need to point it to the correct URL using the `http` transport. -Additionally you'll need to provide an `Authorization` header with your Tilebox API key as the bearer token. +Authentication is handled automatically via OAuth — no API key or headers required. ```json { "mcpServers": { "tilebox": { - "url": "https://mcp.tilebox.com/mcp", - "headers": { - "Authorization": "Bearer " - } + "url": "https://mcp.tilebox.com/mcp" } } } @@ -45,9 +43,28 @@ Additionally you'll need to provide an `Authorization` header with your Tilebox Run the following command to add the Tilebox MCP server to Claude: ```bash -claude mcp add --transport http "Tilebox" https://mcp.tilebox.com/mcp --header "Authorization: Bearer " +claude mcp add --transport http "Tilebox" https://mcp.tilebox.com/mcp ``` + +If you need to access multiple teams, add a separate MCP server instance for each one. For example: + +```json +{ + "mcpServers": { + "tilebox-team1": { + "url": "https://mcp.tilebox.com/mcp" + }, + "tilebox-team2": { + "url": "https://mcp.tilebox.com/mcp" + } + } +} +``` + +Each instance will go through its own OAuth flow, allowing you to authorize a different team. + + ## Providing the full Tilebox documentation as context As an alternative to using the MCP server's documentation search, you can also provide the full Tilebox documentation as context to your AI assistant or language model. From 807212d5fddeb0ba8ca94bcb0f263662671868b8 Mon Sep 17 00:00:00 2001 From: Lukas Bindreiter Date: Wed, 18 Feb 2026 14:21:13 +0100 Subject: [PATCH 2/2] Update github actions --- .../styles/config/vocabularies/docs/accept.txt | 2 ++ .github/workflows/lint.yml | 18 ++++++++---------- ai-assistance.mdx | 4 ++-- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/.github/styles/config/vocabularies/docs/accept.txt b/.github/styles/config/vocabularies/docs/accept.txt index 1289484..a58a8b2 100644 --- a/.github/styles/config/vocabularies/docs/accept.txt +++ b/.github/styles/config/vocabularies/docs/accept.txt @@ -69,3 +69,5 @@ boolean reprojected (?i)geospatial (?i)cartesian +(?i)OAuth + diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml index dcda5f7..01bbf16 100644 --- a/.github/workflows/lint.yml +++ b/.github/workflows/lint.yml @@ -6,19 +6,17 @@ jobs: name: Run Vale Linter runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v6 with: lfs: true - name: Install Vale run: | - VALE_URL="https://github.com/errata-ai/vale/releases/download/v3.12.0/vale_3.12.0_Linux_64-bit.tar.gz" - curl -L "$VALE_URL" -o vale.tar.gz - tar -xzf vale.tar.gz - mv vale /usr/local/bin/ + curl -L "https://github.com/errata-ai/vale/releases/download/v3.13.1/vale_3.13.1_Linux_64-bit.tar.gz" -o vale.tar.gz + tar -xzf vale.tar.gz -C /usr/local/bin vale - name: Setup Node - uses: actions/setup-node@v4 + uses: actions/setup-node@v6 with: - node-version: 22 + node-version: 24 - name: Install MDX preprocessor run: npm install -g mdx2vast - name: Run vale @@ -27,13 +25,13 @@ jobs: name: Check docs standards runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@v6 with: lfs: true - name: Setup Node - uses: actions/setup-node@v4 + uses: actions/setup-node@v6 with: - node-version: 22 + node-version: 24 - name: Install Mintlify CLI run: npm install -g mintlify - name: Run Mintlify broken-links diff --git a/ai-assistance.mdx b/ai-assistance.mdx index 3b66f24..37b570f 100644 --- a/ai-assistance.mdx +++ b/ai-assistance.mdx @@ -20,13 +20,13 @@ The Tilebox MCP server at `https://mcp.tilebox.com/mcp` provides tools for: - Accessing and interacting with Tilebox datasets and workflows - Searching the Tilebox documentation -It requires authentication via OAuth. When connecting, you'll be redirected to sign in with your Tilebox account and select a team to authorize the MCP server for. +It requires authentication via OAuth. When connecting, you'll be redirected to sign in with your Tilebox account and select a team to use the MCP server for. When configured, AI agents can query datasets, interact with workflows, and search the documentation for detailed context on specific topics. ### Configuring the Tilebox MCP server To configure your AI tools to use the Tilebox MCP server, you need to point it to the correct URL using the `http` transport. -Authentication is handled automatically via OAuth — no API key or headers required. +Authentication is handled automatically via OAuth, no API key or headers required. ```json {