Tendeck MCP server
Which MCP servers are Tendeck'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 2026-10-30
- Registry nameai.tendeck/crmverified in the MCP registry
The registry name sits under tendeck.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-30
- Tools9
- Server calls itselftendeck
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 233 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 6 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.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer215 ms
- Space in an agent's context≈ 2,084 tokensthe definitions of all its tools (13), which an agent carries on every turn
- Tool definitionsB · 82 of 100
- Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 13
- Not saying whether it only reads or can destroy: 13 of 13
What an agent can do with it
- not sure · pick the ten contacts to call today
- not sure · draft check-in texts to past clients
- cannot · import contacts from a spreadsheet or another CRM
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
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 →
describe_productPlain-language description of the two Nuvidian products (P1 brokerage recruiting CRM, P2 agent CRM), what is free, and what the product never does.
get_free_limitsWhat each product includes for free, in plain numbers (P1: full pond + pipeline, 3 recruiters; P2: unlimited people/deals, no AI quotas because Tendeck runs no AI of its own, 1 farm list).
list_addonsOptional paid add-ons with their unit and price in cents. Prices only — no costs, no margins.
start_workspaceSign up for free: create a pending workspace and send a 6-digit code to the user's email (preferred) or US phone. Ask the user for the code, then call verify_phone. Idempotent on idem_key. FIRST show the human the Terms of Service…
verify_phoneFinish signup: check the 6-digit code the user received by email (or text), activate the workspace and return a session token.
p1_practice_deckShow a sample of Nuvidian P1's 'Today's 10' deck built from fictional Florida agents, so a human can see what the product does before signing up. Call it when someone asks 'what is P1?' or 'show me'. The cards are unmistakably fake…
p2_practice_todayShow a sample of Nuvidian P2's Today's 10 built from fictional people, so a human can see what the product does before signing up. Call it when someone asks 'what is P2?' or 'show me'. Each card is a fictional person with a plain-English…
tendeck_helpAnswer any how-to or support question about Tendeck (sign-in, password, billing, connecting ChatGPT/Claude, importing, texting, privacy). Call this BEFORE telling the user you don't know.
connectors_catalogWhat Tendeck plugs into: live connectors, the next ones being built, and what is planned, each with what it gives the agent and how to connect. Use it when they ask 'does Tendeck work with X?' or name a tool they use (dotloop, SkySlope…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"crm": {
"type": "http",
"url": "https://tendeck.ai/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http tendeck https://tendeck.ai/mcpclaude.ai, ChatGPT and other clients: add https://tendeck.ai/mcp as a custom connector in the settings.
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.