mcp server
docs-mcp
Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.
Description as published by the maintainer. Source
- version 0.3.2
- active
active — Most recent push to the repository was 2026-08-05.
What this server can do
13 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
answer_how_to(task, limit, audience, docs_ref, engine_version)- Answer how to install or use Tandem, build workflows, or use the SDKs by synthesizing relevant published docs. Required: task.
compare_doc_page_refresh(path, docs_ref)- Force-refresh a docs page and return before/after hashes so page content changes can be proven. Required: path.
compare_docs_index_refresh(docs_ref)- Force-refresh the docs indexes and return before/after hashes so content changes can be proven.
get_doc(path, docs_ref, engine_version)- Fetch and normalize a published Tandem docs page by path or URL. Required: path.
get_docs_cache_status- Inspect the current docs cache state for index sources and warmed pages.
get_start_path(role, docs_ref)- Recommend the best Tandem docs starting path for a desktop user, server admin, or developer. Required: role.
get_tandem_guide(topic, docs_ref)- Return a structured Tandem learning guide for install-engine, python-sdk, typescript-sdk, build-workflows, or headless-deploy. Required: topic.
invalidate_docs_cache(path, target, docs_ref)- Invalidate docs cache entries for index data, all pages, or a specific page path.
recommend_next_docs(goal, limit, docs_ref, current_path)- Recommend the next Tandem docs to read after a current page, optionally biased toward a goal. Required: current_path.
refresh_doc_page(path, docs_ref, force_refresh)- Force-refresh a docs page and report whether content came from the network, cache, or stale fallback. Required: path.
refresh_docs_index(docs_ref, force_refresh)- Force-refresh docs indexes and report whether data came from the network, cache, or stale fallback.
search_docs(limit, query, audience, docs_ref, engine_version)- Search the published Tandem docs index for relevant pages. Required: query.
warmup_docs_cache(docs_ref, force_refresh)- Refresh the docs index and preload the most important Tandem docs pages into cache.
Last successful function declaration observed on . Source: https://tandem.ac/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://tandem.ac/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 114 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-05 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 0.3.2 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-04-22 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-04-22 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 13 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | tandem.ac | |
| mcp endpoint status | ok | The server listed 13 functions when asked. | as of probe | tandem.ac |
Where to get it
Related, by what their authors tagged them
-
freellmpool
— last commit 2026-07-29, shares openai, openrouter
Pool 18 LLM providers through MCP: ask, panel, tokenmax, route, models, quota, and stats.
-
io.github.Daichi-Kudo/llm-advisor
— last commit 2026-06-18, shares openrouter
Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
-
io.github.dcondrey/misterdev
— last commit 2026-07-27, shares openrouter
Autonomous LLM build orchestrator that plans, edits, and verifies code across languages.
-
io.github.developerz-ai/ui-debugger-mcp
— last commit 2026-08-08, shares openrouter
Autonomous UI debugging MCP server: an agent drives the browser/desktop, reports bugs + UX issues.
-
io.github.hashgraph-online/hashnet
— last commit 2026-05-08, shares openrouter
Universal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter
-
Haldir
— last commit 2026-04-22, shares governance, human-in-the-loop
Guardian layer for AI agents: identity, secrets, audit via MCP.
-
io.github.cruxible-ai/cruxible-core
— last commit 2026-08-05, shares governance, local-first
Deterministic decision engine with receipts. Define rules in YAML, query a graph, get proof.
-
aden-hive-hive-browser-edge-cases
— last commit 2026-05-29, shares human-in-the-loop, openai
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like L…
-
aden-hive-hive-hive-browser-automation
— last commit 2026-05-29, shares human-in-the-loop, openai
Required before any browser_* tool call. Teaches the screenshot + browser_click_coordinate workflow that reaches shadow…
-
aden-hive-hive-hive-chart-creation-foundations
— last commit 2026-05-29, shares human-in-the-loop, openai
Required reading whenever any chart_* tool is available. Teaches the one-tool embedding contract (call chart_render → l…
These share tags the maintainers applied themselves, such as openai, openrouter, governance, human-in-the-loop. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: agentic-workflow, anthropic, governance, governed-execution, help-wanted, human-in-the-loop, local-first, openai, openrouter.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json