MCP server for 104.com.tw job search platform
Free
Tools
openmandate_create_mandate
Create a new mandate on OpenMandate. Provide what the user is looking for (want) and what they bring to the table (offer). The user's verified contacts are automatically attached. Returns the mandate with follow-up questions. You MUST relay these questions to the user and collect their actual answers before calling openmandate_submit_answers. Do not answer questions on the user's behalf. If the
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
—
p95 latency
—
call success
—
uptime 90d
0
calls last 7d
What it does
MCP server for OpenMandate — open protocol for bilateral matching.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add mcp-openmandate-ai-openmandate-mcp
# 2 — ask your agent something
> MCP server for OpenMandate — open protocol for bilateral matching.
OpenMandate is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
MCAll 1 server
mcp.openmandate.ai1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add --transport http mcp-openmandate-ai-openmandate-mcp https://mcp.openmandate.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
What you approve
15 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.
Create a new mandate on OpenMandate. Provide what the user is looking for (want) and what they bring to the table (offer). The user's verified contacts are automatically attached. Returns the mandate with follow-up questions. You MUST relay these questions to the user and collect their actual answers before calling openmandate_submit_answers. Do not answer questions on the user's behalf. If the
Takes no parameters.
Example callreturns →
Submit the user's answers to pending intake questions. The mandate must be in 'intake' status with pending questions. IMPORTANT: Before calling this, you must show each pending question to the user and collect their real answer. Never fabricate or infer answers. OpenMandate may return additional questions. Relay each round to the user until the mandate becomes active.
Takes no parameters.
Example callreturns →
Get a mandate by ID. Returns the mandate's current status, any pending intake questions, and summary once active. Use this to check progress or retrieve questions after creating a mandate.
Takes no parameters.
Example callreturns →
List the user's open mandates. Returns non-closed mandates by default. Pass status to filter (e.g. status='closed' for history).
Takes no parameters.
Example callreturns →
Close (withdraw) a mandate. This is permanent — the mandate will stop matching and cannot be reopened. Only close if the user explicitly wants to withdraw.
Takes no parameters.
Example callreturns →
List matches for the authenticated user. Returns matches with compatibility grade, strengths, and concerns. Check this periodically after a mandate becomes active.
Takes no parameters.
Example callreturns →
Get detailed information about a specific match, including compatibility grade, strengths, concerns, and — if both parties accepted — the counterparty's contact information.
Takes no parameters.
Example callreturns →
Accept or decline a match. If you accept and the other party also accepts, contact info is revealed to both sides. Declining is permanent for this match.
Takes no parameters.
Example callreturns →
Report how a confirmed match went. Available after both parties accepted and contact info was revealed. Outcomes: - 'succeeded': Found the right person. Mandate closes. - 'failed': Didn't work out. Mandate reactivates for new matches. - 'ongoing': Still in conversation. OpenMandate checks back later. IMPORTANT: Always confirm the outcome with the user before submitting. This affects their mandat
Takes no parameters.
Example callreturns →
List the user's verified contacts. These are the contacts revealed to the other party on match confirmation. Each contact has an ID, type, display label, and verification status.
Takes no parameters.
Example callreturns →
Add a new contact for the user. A verification code (OTP) will be sent to the contact address. The user must verify the contact using openmandate_verify_contact before it can be used on mandates. The first contact added becomes the primary contact automatically.
Takes no parameters.
Example callreturns →
Verify a contact by submitting the OTP code sent to it. The user must check their email for the 8-digit code. After verification, the contact can be used on mandates.
Takes no parameters.
Example callreturns →
Update a contact's display label or set it as the primary contact. Setting a contact as primary will unset any other primary contact.
Takes no parameters.
Example callreturns →
Delete a contact. If the deleted contact was primary, the next verified contact is automatically promoted. This is permanent.
Takes no parameters.
Example callreturns →
Resend the verification code for a pending contact. Use this if the user didn't receive the code or it expired (codes expire after 10 minutes). Rate limited to 3 per contact per hour.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. OpenMandate costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
—Grade not published
No rule-by-rule report on file for this release
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.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 0.6.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.6.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against OpenMandate in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
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 an account with 50 real tool calls against it.