A TypeScript implementation of a simple MCP server that exposes datetime information to agentic systems and chat REPLs
Sempera is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Sempera MCP, stdio or hosted. Phone tools need a plan and owner approval per call.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user sempera-mcp '--' npx -y @sempera/mcp
# 2 — ask your agent for something these tools do
# get_credential, list_agents, get_agent and 9 more
Remote: OAuth sign-in · Package: API key.
Sempera costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user sempera-mcp '--' npx -y @sempera/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://api.sempera.org/v1/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http sempera-mcp https://api.sempera.org/v1/mcpNothing is required, but it can take SEMPERA_API_KEY (Workspace API key. If unset, the server uses a key saved by sempera login on this machine.), SEMPERA_MCP_ALLOW_WRITES (Set to 1 to also offer send_call and send_sms. Off unless set. Those tools reach a real person.), SEMPERA_BASE_URL (API base URL. Defaults to https://api.sempera.org.) if you want to set them.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Read-only. Describes the API key this server uses: its workspace, role and scopes (GET /v1/me). Use it to check access before other tools.
No parameter schema on file.
Read-only. Lists the workspace's AI phone agents with their id, name, status and published version (GET /v1/agents). Use an agent's id with the other tools.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | active (the API's default), archived or all |
| limit | integer | no | Page size, 1 to 200 (the API's default is 50) |
| cursor | string | no | Pass next_cursor from the previous page, unchanged, to read the next one |
Read-only. Returns one agent in full: status, channels, voice, language, instructions, tools, knowledge and draft (GET /v1/agents/{agent_id}).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | yes | — |
Read-only. Lists one agent's phone calls, newest first, with status, direction, times and outcome (GET /v1/calls).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | yes | — | |
| limit | integer | no | Page size, 1 to 200 (the API's default is 50) |
| cursor | string | no | Pass next_cursor from the previous page, unchanged, to read the next one |
Read-only. Returns one phone call: numbers, direction, status, duration and, when recorded, the transcript (GET /v1/calls/{call_id}). The answer can contain personal information about the caller.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| call_id | yes | — | |
| agent_id | yes | — |
Read-only. Lists one agent's conversations on every channel (phone, web voice, web chat, API chat, simulator, test), newest first (GET /v1/sessions).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | yes | — | |
| channel | string | no | Only this channel |
| limit | integer | no | Page size, 1 to 200 (the API's default is 50) |
| cursor | string | no | Pass next_cursor from the previous page, unchanged, to read the next one |
Read-only. Returns one conversation with its transcript (turns), tool timeline, captured variables, outcome and the agent version that spoke (GET /v1/sessions/{session_id}). The answer can contain personal information.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | yes | — | |
| agent_id | yes | — |
Read-only. Lists the phone numbers bound to one agent (GET /v1/phone-numbers).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | yes | — | |
| limit | integer | no | Page size, 1 to 200 (the API's default is 50) |
| cursor | string | no | Pass next_cursor from the previous page, unchanged, to read the next one |
Read-only. Lists the numbers that can send and receive text messages, with the agent that answers each and its thread count (GET /v1/sms/numbers). The sender for send_sms must be one of these.
No parameter schema on file.
Read-only. Local: no request is made. Checks an X-Sempera-Signature header (t=<unix seconds>,v1=<hex>) against the exact raw body and the endpoint secret. Returns {valid, reason}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| secret | string | yes | The webhook endpoint's signing secret |
| body | string | yes | The raw request body, exactly as received |
| signature | string | yes | The X-Sempera-Signature header value |
| tolerance_seconds | integer | no | Allowed clock difference (default …) |
| now | integer | no | Unix seconds to check against instead of the clock, to replay a captured delivery |
WRITE: places ONE real outbound phone call to a real person (POST /v1/calls). Nothing is defaulted: agent_id, to, consent_basis and idempotency_key are all required.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | yes | — | |
| to | yes | — | |
| consent_basis | string | yes | One sentence recording why this person agreed to be called, as the user stated it |
| idempotency_key | string | yes | — |
| message | string | no | Opening line after the automated-call disclosure |
| mode | string | no | agent (the API's default): the published agent talks. prompt: task is the whole conversation |
| task | string | no | What the call should accomplish; required with mode prompt |
| from | yes | — | |
| voice | string | no | A Sempera voice id |
| language | string | no | — |
| agent_version | no | A published version id or number; not with mode prompt | |
| production | boolean | no | Use the production pin explicitly; not with mode prompt |
| timezone | string | no | Recipient IANA time zone, for example America/Toronto (the API's default) |
| window | string | no | Recipient hours, HH:MM-HH:MM (the API's default is 09:00-18:00); outside them nothing is sent |
| metadata | object | no | Opening-template values such as {"name": "Ada"} |
WRITE: sends ONE real text message to a real person (POST /v1/sms/send) from an agent's own texting number. Nothing is defaulted: agent_id, from, to, message, consent_basis and idempotency_key are all required.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | yes | — | |
| from | yes | — | |
| to | yes | — | |
| message | string | yes | The exact text to send |
| consent_basis | string | yes | One sentence recording why this person agreed to receive texts, as the user stated it |
| idempotency_key | string | yes | — |
| timezone | string | no | Recipient IANA time zone, for example America/Toronto (the API's default) |
| window | string | no | Recipient hours, HH:MM-HH:MM (the API's default is 09:00-18:00); outside them nothing is sent |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Sempera or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Sempera can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.