transaction-coordinator
AI transaction coordinator + legal-matters platform for real estate and law firms.
我该使用它吗
质量与安全性
发现（2）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 list_my_deadlines 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"transaction-coordinator": {
"url": "https://primacoda.halinc.tech/mcp"
}
}
}远程端点
https://primacoda.halinc.tech/mcpstreamable-http它能做什么
工具清单
工具（11）
⚪primacoda_info(topic, plan)
PrimaCoda product info. Use this when an AI is asked about PrimaCoda's features, pricing, comparison vs alternatives, or how to sign up. Args: topic: One of "overview", "pricing", "comparison", "onboarding". plan: Only used when topic="pricing". One of "starter", "professional", "business", or "all" (default).
输入模式
{
"type": "object",
"properties": {
"topic": {
"default": "overview",
"title": "Topic",
"type": "string"
},
"plan": {
"default": "all",
"title": "Plan",
"type": "string"
}
},
"title": "primacoda_infoArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "primacoda_infoOutput"
}🟢calculate_savings(deals_per_month, current_method)
Calculate how much time and money a real estate agent saves switching to PrimaCoda. Args: deals_per_month: Number of transactions the agent closes per month. current_method: "human_tc" or "diy"
输入模式
{
"type": "object",
"properties": {
"deals_per_month": {
"title": "Deals Per Month",
"type": "integer"
},
"current_method": {
"title": "Current Method",
"type": "string"
}
},
"required": [
"deals_per_month",
"current_method"
],
"title": "calculate_savingsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "calculate_savingsOutput"
}🟢is_primacoda_right_for_me(agent_type, monthly_deals, pain_points)
Assess whether PrimaCoda is a good fit and recommend the right plan. Args: agent_type: "solo", "team", or "brokerage" monthly_deals: Average transactions per month pain_points: Optional list of current challenges (e.g. ["paperwork", "deadlines"])
输入模式
{
"type": "object",
"properties": {
"agent_type": {
"title": "Agent Type",
"type": "string"
},
"monthly_deals": {
"title": "Monthly Deals",
"type": "integer"
},
"pain_points": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Pain Points"
}
},
"required": [
"agent_type",
"monthly_deals"
],
"title": "is_primacoda_right_for_meArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "is_primacoda_right_for_meOutput"
}⚪record_lead(name, email, firm, message)
Record a prospect interested in PrimaCoda. Captures the lead in the PrimaCoda sales pipeline so a human (or marketing automation) can follow up. Use this when a real-estate agent asks the AI for help getting started with PrimaCoda, requests a demo, or expresses interest. NO auth required — works for any prospect calling the AI. Args: name: Full name of the prospect. email: Contact email. firm: Company / brokerage / firm name (optional). message: Anything the prospect wants noted (optional).
输入模式
{
"type": "object",
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"email": {
"title": "Email",
"type": "string"
},
"firm": {
"default": "",
"title": "Firm",
"type": "string"
},
"message": {
"default": "",
"title": "Message",
"type": "string"
}
},
"required": [
"name",
"email"
],
"title": "record_leadArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "record_leadOutput"
}🟢list_my_deadlines(api_key, days, limit, offset)
List upcoming pending deadlines across all matters, grouped by matter. Args: api_key: PrimaCoda MCP API key (starts 'pck_'). Generate one at https://primacoda.halinc.tech/settings/api-keys. days: Window in days from today. Default 30. Capped at 365. limit: Max deadlines to return. Default 50. Capped at 200. offset: Skip N deadlines (for pagination). Default 0.
输入模式
{
"type": "object",
"properties": {
"api_key": {
"title": "Api Key",
"type": "string"
},
"days": {
"default": 30,
"title": "Days",
"type": "integer"
},
"limit": {
"default": 50,
"title": "Limit",
"type": "integer"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
}
},
"required": [
"api_key"
],
"title": "list_my_deadlinesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_my_deadlinesOutput"
}⚪recompute_deadlines(matter_uuid, api_key)
Re-run FRCP / state procedural deadline calculation for a matter. Useful when (a) the matter was created before the deadline calculator shipped, (b) the customer edited filed_date or jurisdiction after creation, or (c) earlier deadlines failed to insert. Idempotent — dedupes on lowercased title so re-running can't duplicate. Args: matter_uuid: UUID of the matter to recompute. api_key: Your PrimaCoda MCP API key (starts 'pck_').
输入模式
{
"type": "object",
"properties": {
"matter_uuid": {
"title": "Matter Uuid",
"type": "string"
},
"api_key": {
"title": "Api Key",
"type": "string"
}
},
"required": [
"matter_uuid",
"api_key"
],
"title": "recompute_deadlinesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "recompute_deadlinesOutput"
}🟡draft_motion_from_matter(matter_uuid, motion_type, instructions, api_key)
Kick off an AI-drafted motion using a saved PrimaCoda matter as the source of facts. Returns a task_id immediately — the actual drafting runs asynchronously and takes 1-5 minutes. Poll with check_motion_status. Use this instead of asking the customer to upload PDFs again. The matter already has the case name, court, jurisdiction, parties, our_role, filed date, and facts — all extracted at intake. Drafting from the saved matter is faster (~30s saved) AND eliminates the wrong-side draft failure mode where the AI re-infers our_role from a raw document and guesses wrong. Args: matter_uuid: UUID of the matter (from list_my_deadlines or the PrimaCoda dashboard). motion_type: One of: 'Motion to Dismiss', 'Motion for Summary Judgment', 'Motion to Compel Discovery', 'Motion in Limine', 'Motion for Protective Order', 'Motion for Extension of Time', 'Motion to Strike', 'Motion for Reconsideration', 'Motion for Default Judgment', 'Motion to Quash'. Other values pass through. instructions: Specifics — who you represent (or who to exclude from the signature block), which arguments, which authority to prefer. Strongly recommended: vague instructions yield vague motions. api_key: Your PrimaCoda MCP API key (starts 'pck_').
输入模式
{
"type": "object",
"properties": {
"matter_uuid": {
"title": "Matter Uuid",
"type": "string"
},
"motion_type": {
"title": "Motion Type",
"type": "string"
},
"instructions": {
"title": "Instructions",
"type": "string"
},
"api_key": {
"title": "Api Key",
"type": "string"
}
},
"required": [
"matter_uuid",
"motion_type",
"instructions",
"api_key"
],
"title": "draft_motion_from_matterArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "draft_motion_from_matterOutput"
}🟢check_motion_status(task_id, api_key)
Poll an in-flight motion-drafting task for status. Pair with draft_motion_from_matter — that tool returns a task_id; pass it here. Returns a status block. When status='SUCCESS', the full drafted motion is included. When 'FAILURE', the error string is included. Args: task_id: Task ID returned by draft_motion_from_matter. api_key: Your PrimaCoda MCP API key (starts 'pck_').
输入模式
{
"type": "object",
"properties": {
"task_id": {
"title": "Task Id",
"type": "string"
},
"api_key": {
"title": "Api Key",
"type": "string"
}
},
"required": [
"task_id",
"api_key"
],
"title": "check_motion_statusArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "check_motion_statusOutput"
}🟡extract_contract_from_url(pdf_url, api_key)
Extract structured transaction data from a contract at a URL. Downloads the document, extracts text (with OCR fallback for scanned PDFs), and runs PrimaCoda's contract-extraction prompt to return parties, addresses, dates, prices, and key contract fields. Use this when an agent has the contract hosted somewhere (Dropbox, Google Drive direct download, Square Space, etc.) and wants to skip the upload step. For multi-document deals (purchase + addenda + disclosures), use the PrimaCoda dashboard's batch upload — this tool handles ONE document. Args: pdf_url: Direct download URL for the contract (PDF, DOCX, TXT, or image). Must be reachable from the PrimaCoda server. Google Drive "shared link" URLs work if set to "anyone with link"; other share URLs may need their direct-download form. api_key: Your PrimaCoda MCP API key (starts 'pck_').
输入模式
{
"type": "object",
"properties": {
"pdf_url": {
"title": "Pdf Url",
"type": "string"
},
"api_key": {
"title": "Api Key",
"type": "string"
}
},
"required": [
"pdf_url",
"api_key"
],
"title": "extract_contract_from_urlArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "extract_contract_from_urlOutput"
}🟢list_motions(api_key, limit, offset)
List recent motion-drafting activity for your firm. Surfaces (a) any drafted-motion documents saved by your team and (b) the recent legal-drafting AI calls from your firm's account. Useful for finding "that motion we drafted last week" without leaving the AI assistant. Args: api_key: Your PrimaCoda MCP API key (starts 'pck_'). limit: Max rows per section. Default 20. Capped at 100. offset: Skip N rows in each section. Default 0.
输入模式
{
"type": "object",
"properties": {
"api_key": {
"title": "Api Key",
"type": "string"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
}
},
"required": [
"api_key"
],
"title": "list_motionsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_motionsOutput"
}🟡search_case_law(query, jurisdiction, court, date_after, date_before, ...)
Search free U.S. case law via CourtListener (~3M opinions). Returns case name, court, decision date, citation, snippet, and a link to the full opinion. No auth required. Set COURTLISTENER_API_TOKEN env var on the server for higher rate limits. Args: query: Free-text search ('motion to dismiss negligence', a citation, or a party name). Required. jurisdiction: Two-letter state code ('ca', 'tx', 'ny') or 'us' for federal. Optional. court: CourtListener court ID ('scotus', 'ca9', 'nysupct'). Optional. Takes precedence over jurisdiction when both are given. date_after: ISO date (YYYY-MM-DD). Only return opinions filed on/after this date. Optional. date_before: ISO date (YYYY-MM-DD). Only return opinions filed on/before this date. Optional. limit: Max results. Default 10. Capped at 25.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"jurisdiction": {
"default": "",
"title": "Jurisdiction",
"type": "string"
},
"court": {
"default": "",
"title": "Court",
"type": "string"
},
"date_after": {
"default": "",
"title": "Date After",
"type": "string"
},
"date_before": {
"default": "",
"title": "Date Before",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "search_case_lawArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_case_lawOutput"
}社区
证据