
TridentStack MCP server
Which MCP servers are TridentStack's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-11-18
- Registry namecom.tridentstack/docsverified in the MCP registry
The registry name sits under tridentstack.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-18
- Tools3
- Server calls itselftridentstack-docs
- Server version1.0.0
- Protocol version2025-06-18
On 2026-11-18 the server answered initialize and tools/list without a sign-in. First answer in 139 ms.
Should an agent connect it
- On Nov 18, 2026 we called its read-only tools following a fixed scenario, and 1 of 1 steps returned what the check expects.
- Checked on 4 of the 7 days it takes to judge reliability.
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.
Measured daily
- INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
- Checked by calling it1 of 1 steps passedlatest run Nov 18, 2026, read-only calls only
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer132 ms
- Space in an agent's context≈ 464 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
Worth a look
None of the five warning signs in these definitions.
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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 →
search_docsverified Nov 18, 2026Full-text search over TridentStack Control's customer documentation (guides, API reference, changelog, roadmap). Returns ranked results with titles, URLs, and snippets. Use this first to find relevant docs, then get_doc to read one in…
get_docdescribed by the serverReturn the full markdown of a single documentation chunk by its id (from a search_docs result). Only ids present in the index are valid; this never fetches arbitrary URLs.
list_docsseen, not called yetList the documentation catalog (id, title, source, url), optionally filtered to one content type. Use to browse structure before searching.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"docs": {
"type": "http",
"url": "https://docs.tridentstack.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http tridentstack https://docs.tridentstack.com/mcpclaude.ai, ChatGPT and other clients: add https://docs.tridentstack.com/mcp as a custom connector in the settings.
OpenAPI spec
231 paths, read 2026-11-18. Open the spec ↗
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.
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.