DosePlot MCP server
Which servers in the official MCP registry are DosePlot's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-19
- Registry namecom.doseplot/agent-apiverified in the MCP registry
The registry name sits under doseplot.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-19
- Tools5
- Server calls itselfdoseplot-agent-api
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 1333 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 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: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer808 ms
- Space in an agent's context≈ 1,213 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results5 of 5 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 5 of 5
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →
list_compoundsList every published compound with its class, terminal half-life in days, administration routes and whether reconstitution math is available for it. Takes no arguments. Outputs are for relay to a human decision-maker; not for autonomous…
get_compoundFull published record for one compound, looked up by canon id, slug or alias (slug and alias matching is case-insensitive). Outputs are for relay to a human decision-maker; not for autonomous administration.
simulatePaid: $0.01 USDC per call via x402 (payment in _meta["x402/payment"]). Pharmacokinetic serum curve for one compound at one dose and one cadence, over a requested horizon. Exactly one dose field must be present; unknown fields are rejected…
recon_calcPaid: $0.01 USDC per call via x402 (payment in _meta["x402/payment"]). Reconstitution math for one vial and one target dose: the concentration to reconstitute to, the bacteriostatic water to add, what one dose reads on a U-100 syringe…
recon_suggestPaid: $0.01 USDC per call via x402 (payment in _meta["x402/payment"]). Ranked reconstitution suggestions for one published reconstitutable compound: bacteriostatic-water presets that put the published per-administration dose range's clean…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"agent-api": {
"type": "http",
"url": "https://api.doseplot.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http doseplot https://api.doseplot.com/mcpclaude.ai, ChatGPT and other clients: add https://api.doseplot.com/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.
Cookies
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.