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 2 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: 2 so far
- Answeredmeasuring2 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
- 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.