What can you do with this server?

A read-only MCP server exposing Meissasoft BD Leads CRM analytics and lead data to AI clients like Cursor and Claude Desktop. * list_metadata: Retrieve all custom fields (with options) and pipeline states — valid filter values for other tools. Use this first. * get_win_rate: Win rate overall or sliced by BD rep, profile, lead source, country, or contract type. * get_conversion_funnel: Stage-by-stage funnel (Applied → Won) with per-step conversion %, drop-off counts, and biggest-leak stage. * get_connects_economics: Upwork connects ROI — connects-per-win, spend, estimated revenue-per-connect, wasted connects, and boosted vs. non-boosted comparison, segmented by profile or country. * get_velocity_and_cycle: Sales velocity ($/day) with its four inputs, plus average cycle length broken down by profile and country. * get_forecast: Weighted pipeline forecast — open leads × stage win-probability × estimated deal value — with a per-stage breakdown. * list_leads: Paginated BD leads (up to 200/page) with key and custom fields, filterable by state, profile, country, and date range. Constraints: All tools are read-only (no create/edit/delete). Requires a CRM Personal Access Token from a workspace admin. Date filtering supports presets (e.g. this_month, last_3_months) or explicit start_date/end_date ranges.

How do I use bd-crm-analytics?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@bd-crm-analytics What's our win rate by profile this quarter?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

bd-crm-analytics

by Hammad-Tariq007

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

BD CRM Analytics — MCP server

A read-only MCP server that exposes the Meissasoft BD Leads CRM analytics (win rate, conversion funnel, connects economics, sales velocity, forecast, and lead lookup) to MCP clients like Cursor and Claude Desktop.

It talks only to the CRM public API (/api/v1/) using a Personal Access Token (X-Api-Key). It never writes anything — every tool is a GET. What a token can see is governed entirely by the CRM: a token only returns analytics if its owning user is a workspace admin AND (the workspace owner OR has been granted analytics access).

Tools

Tool	What it returns
`list_metadata`	Custom fields (+ their options) and pipeline states — the valid values for filters. Call this first to discover profiles/countries/contract types/states.
`get_win_rate`	Win rate. `dimension="bd"` → overall + per-rep; `profile`/`lead_source`/`country`/`contract_type` → win rate sliced by that field.
`get_conversion_funnel`	Applied → … → Won funnel with per-step conversion %, drop-off, and biggest-leak stage.
`get_connects_economics`	Connects-per-win overall, ROI by segment (spend, connects/win, est. revenue-per-connect, wasted connects), and boosted-vs-not. `dimension="profile"
`get_velocity_and_cycle`	Sales velocity ($/day) with its 4 inputs, plus avg cycle length by Profile and Country.
`get_forecast`	Weighted pipeline forecast (open leads × stage win-probability × est. deal value) with per-stage breakdown.
`list_leads`	Paginated leads with key fields + BD custom fields. Filter by `state`, `profile`, `country`, date range; `limit`/`offset`.

Analytics tools accept an optional date range: date_filter (e.g. this_month, last_month, last_3_months) or an explicit start_date/end_date (YYYY-MM-DD). Omit for all-time.

Related MCP server: Uniware Vtiger MCP Server

1. Prerequisites

Node.js 18+ (uses the built-in fetch).

2. Install & build

cd bd-crm-mcp
npm install
npm run build      # compiles to dist/

3. Mint a CRM Personal Access Token

Sign in to the CRM (e.g. https://bd-crm.meissasoft.com) as a user who can see BD Insights — i.e. a workspace admin who is the workspace owner or has been granted analytics access. (If your token's user isn't allowed, every tool returns a clear 403 — that's expected.)
Go to Profile → Settings → Personal access tokens (API tokens) and create a token.
Copy it — it looks like plane_api_xxxxxxxx…. Store it as CRM_API_TOKEN.

Find the other values:

WORKSPACE_SLUG — the workspace segment in the CRM URL, e.g. bd-leads in …/bd-leads/projects/….
PROJECT_ID — open the BD Leads project; it's the UUID in the URL: …/projects/<PROJECT_ID>/….

4. Environment variables

Var	Example	Notes
`CRM_BASE_URL`	`https://bd-crm.meissasoft.com`	No trailing slash.
`CRM_API_TOKEN`	`plane_api_…`	Sent as `X-Api-Key`.
`WORKSPACE_SLUG`	`bd-leads`
`PROJECT_ID`	`99361d89-…`	The BD Leads project UUID.

For local testing you can copy .env.example to .env; when wired into a client, set them in the client config (below) instead.

5. Configure your MCP client

Use the absolute path to the built dist/index.js.

Cursor

Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json in your project:

{
  "mcpServers": {
    "bd-crm-analytics": {
      "command": "node",
      "args": ["/absolute/path/to/bd-crm-mcp/dist/index.js"],
      "env": {
        "CRM_BASE_URL": "https://bd-crm.meissasoft.com",
        "CRM_API_TOKEN": "plane_api_xxxxxxxxxxxxxxxxxxxx",
        "WORKSPACE_SLUG": "bd-leads",
        "PROJECT_ID": "99361d89-81b6-4eee-83a6-24e622182383"
      }
    }
  }
}

Reload Cursor; the bd-crm-analytics tools appear in the MCP tool list.

Claude Desktop

Edit the config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "bd-crm-analytics": {
      "command": "node",
      "args": ["/absolute/path/to/bd-crm-mcp/dist/index.js"],
      "env": {
        "CRM_BASE_URL": "https://bd-crm.meissasoft.com",
        "CRM_API_TOKEN": "plane_api_xxxxxxxxxxxxxxxxxxxx",
        "WORKSPACE_SLUG": "bd-leads",
        "PROJECT_ID": "99361d89-81b6-4eee-83a6-24e622182383"
      }
    }
  }
}

Fully quit and reopen Claude Desktop. Ask e.g. "What's our win rate by profile this quarter?" or "Show the conversion funnel and biggest leak."

Windows note: if node isn't on Claude Desktop's PATH, use its full path (e.g. "command": "C:\\Program Files\\nodejs\\node.exe") and a double-backslashed args path.

Hosted service — web chat + remote MCP (`server/`)

Everything above is the local stdio server, unchanged. The same repo also ships a hosted service (server/) that reuses the same CrmClient and the same 7 tools, and adds three network surfaces behind one URL (https://bd-crm.meissasoft.com/mcp):

Surface	Route	Who it's for	Gate
Web chat UI	`GET /mcp`	People in a browser	Login → httpOnly session cookie
Chat backend	`POST /mcp/chat`	(the UI)	Session cookie
Remote MCP	`POST /mcp/rpc` (alias `/mcp/sse`)	Claude Desktop	`Authorization: Bearer <your CRM token>` (or `X-Api-Key`)

Auth model. Login is separate from data fetching. To sign in, a person presents their own CRM personal token; the service verifies it passes the analytics gate (workspace admin and owner-or-analytics-flag), captures their identity, then discards the token. All data is fetched with a single server-side CRM_ADMIN_TOKEN — the browser never sees it, and the ANTHROPIC_API_KEY is server-side only. The remote MCP endpoint uses the same check on the token sent in its header.

Environment (hosted only)

Var	Example	Notes
`CRM_BASE_URL`	`https://bd-crm.meissasoft.com`	CRM public API base.
`CRM_ADMIN_TOKEN`	`plane_api_…`	Owner-level token; does all data fetching. Never sent to the browser.
`LLM_API_KEY`	`sk-or-v1-…`	Chat backend key — any OpenAI-compatible provider (OpenRouter). Server-side only. Blank ⇒ chat disabled.
`LLM_BASE_URL`	`https://openrouter.ai/api/v1`	OpenAI-compatible base URL. Defaults to OpenRouter.
`LLM_MODEL`	`anthropic/claude-sonnet-5`	Model slug. Defaults to Claude Sonnet on OpenRouter.
`WORKSPACE_SLUG`	`bd-leads`
`PROJECT_ID`	`99361d89-…`	BD Leads project UUID.
`SESSION_SECRET`	32+ random bytes	Signs the session cookie. `node -e "console.log(require('crypto').randomBytes(32).toString('hex'))"`
`PORT`	`8787`	Listen port.
`NODE_ENV`	`production`	In prod, gives cookies the `Secure` flag.

The chat backend calls an OpenAI-compatible chat/completions API (OpenRouter by default), so the provider is just LLM_BASE_URL + LLM_API_KEY. The model is pinned in one place — DEFAULT_LLM_MODEL in server/config.ts (currently anthropic/claude-sonnet-5) — and any deploy can override it with LLM_MODEL. Only the LLM-call layer is provider-specific; the 7 tools and the CrmClient (env admin token) wiring are unchanged.

Mint CRM_ADMIN_TOKEN: sign in to the CRM as the workspace owner (or an admin with analytics access), go to Profile → Settings → Personal access tokens, create one, and set it as CRM_ADMIN_TOKEN. This is the only token stored, and it lives only in the server env.

Run locally

npm install
npm run build:server
CRM_BASE_URL=http://localhost:8001 \
CRM_ADMIN_TOKEN=plane_api_… \
WORKSPACE_SLUG=bd-leads \
PROJECT_ID=99361d89-… \
SESSION_SECRET=$(node -e "console.log(require('crypto').randomBytes(32).toString('hex'))") \
LLM_API_KEY=sk-or-v1-…  \
PORT=8790 npm run start:server
# open http://localhost:8790/mcp   (dev live-reload: npm run dev:server)

Connect Claude Desktop to the remote MCP endpoint

Add this to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/…, Windows: %APPDATA%\Claude\…). It uses mcp-remote to bridge stdio ↔ the remote HTTP endpoint, sending your own CRM token as a header:

{
  "mcpServers": {
    "bd-crm-analytics": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://bd-crm.meissasoft.com/mcp/rpc",
        "--header", "X-Api-Key:plane_api_xxxxxxxxxxxxxxxxxxxx"
      ]
    }
  }
}

X-Api-Key:<token> (no space) sidesteps a known mcp-remote header-parsing quirk. If you prefer a bearer token, use "--header", "Authorization:Bearer plane_api_…" — but keep it one token with no space after the header name, or pass it via an env-substituted value. Fully quit and reopen Claude Desktop; the tools appear. Your token must pass the analytics gate or every call returns a readable 401/403.

Deploy (reference — not auto-applied)

Nothing environment-specific is hardcoded — the service reads everything from env, so dev and prod differ only by their .env file:

.env.local.example — dev values (CRM_BASE_URL=http://localhost:8001, dev PROJECT_ID).
.env.prod.example — prod values (CRM_BASE_URL=https://bd-crm.meissasoft.com, prod PROJECT_ID).

Both carry placeholders only for CRM_ADMIN_TOKEN, LLM_API_KEY, SESSION_SECRET.

Build & push the image to GHCR (same flow as the CRM image), then deploy from it:

export MCP_IMAGE_TAG=$(git rev-parse --short HEAD)      # or a semver, e.g. v1.0.0
echo "$GHCR_PAT" | docker login ghcr.io -u <github-username> --password-stdin
docker build -t ghcr.io/meissasoft/bd-crm-mcp:$MCP_IMAGE_TAG \
             -t ghcr.io/meissasoft/bd-crm-mcp:latest .
docker push ghcr.io/meissasoft/bd-crm-mcp:$MCP_IMAGE_TAG
docker push ghcr.io/meissasoft/bd-crm-mcp:latest

On the host:

cp .env.prod.example .env      # then fill the 3 secrets
docker compose up -d bd-crm-mcp

Dockerfile — builds server/ and runs server/dist/server/main.js on PORT.
deploy/docker-compose.snippet.yml — isolated service block; image: from GHCR, every value via ${VAR} (no baked IDs/URLs). Caddy network is a TODO to fill after inspecting the stack.
deploy/Caddyfile.snippet — routes /mcp/* to the container (flush_interval -1 for SSE).

Deploy is a separate, deliberate step: push the image, set the .env, add the container + Caddy route, and confirm the CRM app is untouched.

Behavior & troubleshooting

Read-only. No tool creates, edits, or deletes anything.
401 → token missing/invalid/expired: check CRM_API_TOKEN.
403 → the token's user lacks analytics access (needs workspace admin + owner-or-flag).
404 → check CRM_BASE_URL and WORKSPACE_SLUG.
Errors are returned as readable tool results; the server does not crash.
Estimated figures (deal value, revenue-per-connect, velocity, forecast) come straight from the CRM's deal-value proxy and are labelled as estimates there.

Development

npm run dev     # run from source with tsx (no build step)

Available Tools

7 tools

get_connects_economicsA

Upwork connects economics: overall connects-per-win, connects ROI by segment (spend, connects/win, estimated revenue-per-connect, wasted connects) and a boosted-vs-not comparison.

ParametersJSON Schema

Name	Required	Description	Default
`end_date`	No	Custom range end (YYYY-MM-DD). Use with start_date.
`dimension`	No	Segment for the ROI table.	profile
`start_date`	No	Custom range start (YYYY-MM-DD). Use with end_date.
`date_filter`	No	Preset range, e.g. "this_month", "last_month", "last_3_months". Omit for all time.

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It states the tool returns economic metrics but does not explicitly declare the operation type (read-only), mention side effects, auth needs, or rate limits. The behavior is partially transparent through the listed outputs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the key outputs. It is concise with no redundancy, though it could benefit from slight structural separation for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no output schema, and no annotations, the description provides a reasonable overview but lacks details on return format, required parameters (none required), and how the filters affect results. It is adequate but not fully self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter having a description. The tool description adds minimal extra meaning beyond the schema; it mentions 'segment' which aligns with the 'dimension' parameter but does not elaborate on usage or constraints. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as providing 'connects economics' metrics like overall connects-per-win, segmented ROI data, and boosted-vs-not comparison, using a specific verb (implied 'get') and resource. It distinguishes from sibling tools like get_conversion_funnel or get_forecast by the focus on connects economics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by listing the output metrics, but does not explicitly state when to use this tool versus alternatives or provide any contextual guidance. No exclusions or when-not-to-use information is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_conversion_funnelB

Stage-conversion funnel (Applied → … → Won) with per-step conversion %, drop-off, and the biggest-leak stage. Snapshot of current pipeline positions.

ParametersJSON Schema

Name	Required	Description
`end_date`	No	Custom range end (YYYY-MM-DD). Use with start_date.
`start_date`	No	Custom range start (YYYY-MM-DD). Use with end_date.
`date_filter`	No	Preset range, e.g. "this_month", "last_month", "last_3_months". Omit for all time.

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description should disclose behavioral traits. It only mentions a snapshot of current pipeline positions but fails to describe whether the operation is read-only, any side effects, or limitations like data freshness or pagination.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences. The first sentence front-loads the main purpose and key metrics, and the second adds context without waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the output includes per-step conversion %, drop-off, and biggest-leak stage, which is helpful but lacks specifics on the exact structure or fields returned. Given no output schema, more detail on output format would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters are described in the schema (100% coverage). The description mentions custom and preset ranges, but this adds little beyond the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides a stage-conversion funnel with per-step conversion percentages, drop-off, and the biggest-leak stage. It distinguishes itself from sibling tools like get_forecast and get_win_rate by focusing on pipeline positions and conversion steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lacks explicit guidance on when to use this tool versus alternatives. No context on prerequisites, exclusions, or best-fit scenarios is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_forecastA

Weighted pipeline forecast: total estimated value of open leads, each weighted by its stage's win probability, with a per-stage breakdown. Deal value is an estimate.

ParametersJSON Schema

Name	Required	Description
`end_date`	No	Custom range end (YYYY-MM-DD). Use with start_date.
`start_date`	No	Custom range start (YYYY-MM-DD). Use with end_date.
`date_filter`	No	Preset range, e.g. "this_month", "last_month", "last_3_months". Omit for all time.

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description notes deal value is an estimate but omits details on data freshness, recalculation logic, or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences front-loading key functionality with zero unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, description hints at per-stage breakdown; covers essential purpose but could clarify default range behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema provides full parameter descriptions (100% coverage); description adds no extra meaning beyond what schema already offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool computes a weighted pipeline forecast with per-stage breakdown, distinguishing it from siblings like win rate or conversion funnel.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives; lacks context on prerequisites or exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_velocity_and_cycleA

Sales velocity ($/day) with its four inputs (open opps, avg deal value, win rate, avg cycle length), plus average cycle length (created → Won) broken down by Profile and by Country.

ParametersJSON Schema

Name	Required	Description
`end_date`	No	Custom range end (YYYY-MM-DD). Use with start_date.
`start_date`	No	Custom range start (YYYY-MM-DD). Use with end_date.
`date_filter`	No	Preset range, e.g. "this_month", "last_month", "last_3_months". Omit for all time.

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses the output structure (velocity, inputs, cycle length breakdowns) but does not mention behavioral traits like being read-only, idempotent, or any permissions needed. It is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with no fluff. It efficiently conveys the core output and breakdown dimensions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given moderate complexity, the description covers the return structure adequately without needing an output schema. It explains what metrics are returned and the breakdowns. Leaves out only minor details like data format or freshness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter is described in the schema. The description adds no additional meaning beyond what the schema provides (date range filters). Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns 'Sales velocity ($/day) with its four inputs' and 'average cycle length broken down by Profile and by Country'. The verb 'get' plus the specific resource 'velocity_and_cycle' is precise, and the breakdown distinguishes it from sibling tools like 'get_win_rate' or 'get_conversion_funnel'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for sales velocity and cycle analysis but lacks any explicit guidance on when to use this tool versus alternatives (e.g., when to prefer this over get_win_rate or get_forecast). No exclusions or context dependency mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_win_rateA

Win rate for the BD Leads pipeline. dimension='bd' gives overall + per-BD-rep win rates; dimension in profile|lead_source|country|contract_type gives win rate sliced by that field (leads, wins, closed and win % per value).

ParametersJSON Schema

Name	Required	Description	Default
`end_date`	No	Custom range end (YYYY-MM-DD). Use with start_date.
`dimension`	No	How to slice win rate.	bd
`start_date`	No	Custom range start (YYYY-MM-DD). Use with end_date.
`date_filter`	No	Preset range, e.g. "this_month", "last_month", "last_3_months". Omit for all time.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It explains the slicing behavior and output structure (leads, wins, closed, win %), though it omits details like read-only nature or rate limits. This is adequate but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence. It front-loads the purpose and efficiently conveys the two main use cases without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema, the description hints at the return format (leads, wins, closed, win %). For a 4-param tool with no required parameters, this is fairly complete, though it could mention default behavior or typical usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (all params described). The description adds significant value for 'dimension' by explaining the difference between 'bd' and other values. For date parameters, it adds no extra meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool calculates win rate for the BD Leads pipeline and distinguishes two modes: dimension='bd' gives overall and per-rep rates, while other dimensions slice by field. This specificity distinguishes it from sibling tools like get_conversion_funnel.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the effect of different dimension values, providing clear context for when to use each. However, it does not explicitly compare to sibling tools or state when not to use this tool, leaving a minor gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_leadsA

List BD leads (read-only, paginated) with key fields + BD custom fields. Filter by state (name or group), profile, country, and date range. Use list_metadata for valid values.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Page size (max 200).
`state`	No	State name (e.g. "Won") or group (backlog\|unstarted\|started\|completed\|cancelled).
`offset`	No	Rows to skip (pagination).
`country`	No	Country option name (exact).
`profile`	No	Profile option name (exact).
`end_date`	No	Custom range end (YYYY-MM-DD). Use with start_date.
`start_date`	No	Custom range start (YYYY-MM-DD). Use with end_date.
`date_filter`	No	Preset range, e.g. "this_month", "last_month", "last_3_months". Omit for all time.

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses read-only and paginated behavior, which are key traits. However, with no annotations provided, the description carries full burden. It does not mention rate limits, authentication requirements, sorting order, or error conditions, leaving some behavioral aspects implicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no filler. The first sentence captures the core purpose, the second lists filter capabilities, and the third provides cross-reference. Every sentence adds unique value and the front-loading is optimal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 optional parameters, no output schema, and no annotations, the description covers the tool's purpose, read-only nature, pagination, filters, and where to get valid values. It does not detail pagination parameters (but schema covers them) or explicitly state the output format beyond 'key fields + custom fields', which is sufficient for a list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by summarizing filter categories (state, profile, country, date range) and directing to list_metadata for valid values, which goes beyond individual parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists BD leads with key fields and custom fields, specifies read-only and paginated behavior, and enumerates filter dimensions. It is distinct from all sibling tools (analytics reports and metadata lookup), so there is no ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: use this tool to list leads with pagination and filters. It recommends list_metadata for valid filter values, which is helpful. However, it does not explicitly exclude any scenarios or compare with alternatives; since no sibling does the same thing, this is a minor gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_metadataA

List available custom fields (with their options) and pipeline states — the valid values for filtering (profiles, countries, contract types, states). Call this first to discover filters.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool lists metadata, which implies a read-only operation, but it does not explicitly confirm no side effects, authentication requirements, or rate limits. For a simple listing tool, this is adequate but lacks explicit transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, direct sentence that immediately states the action and resource. It is front-loaded with the most important information and contains no fluff. Every word contributes meaning, making it highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and no output schema, the description adequately explains what the tool does and its purpose (discover filters). However, it does not describe the output format or any potential limits. For a simple metadata tool, this is sufficient but just shy of fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and schema coverage is 100% (empty schema). The description adds no parameter information because none exist. According to guidelines, 0 parameters gives a baseline of 4. The description does not need to compensate for missing parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and the resource: 'available custom fields (with their options) and pipeline states'. It explicitly states that these are valid values for filtering, distinguishing it from sibling tools like list_leads which list leads, not metadata. The instruction 'Call this first to discover filters' further clarifies its unique role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear when-to-use directive: 'Call this first to discover filters.' This implies it should be used before utilizing filter parameters in other tools. However, it does not explicitly mention when not to use it or provide alternatives, which prevents a top score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

7 tool updatesv1.0.0Jul 14, 2026
- First observedget_connects_economics
- First observedget_conversion_funnel
- First observedget_forecast
- First observedget_velocity_and_cycle
- First observedget_win_rate
- First observedlist_leads
- First observedlist_metadata

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored 2026-07-14 08:40 across 7 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: economics metrics, conversion funnel, forecast, velocity/cycle, win rate, leads listing, and metadata discovery. No overlap in functionality.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern using 'get_' for metrics and 'list_' for data retrieval. The naming is uniform and predictable.

Tool Count5/5

Seven tools is appropriate for a CRM analytics server, covering key analytic dimensions without being overwhelming or too sparse.

Completeness5/5

The tool set covers the primary analytics needs: economics, funnel, forecast, velocity, win rates, plus leads listing and metadata. No obvious gaps for the intended purpose.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Relm CRM A
com.relmcrm
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
CRM AI & Machine Learning
412
convalytics A
io.github.Dan-Cleary
Read-only analytics for Convex apps, queryable via MCP from Claude, Cursor, and other clients.
Developer Tools Monitoring Databases
1526
HubSpotOAuth
com.hubspot.app
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
Customer Data Platforms Databases Marketing
3
classquill-mcp
io.github.EquateItAu
Read-only MCP server for ClassQuill, a tutoring-business-management platform.
Education & Learning Tools CRM
2

Related MCP Servers

pipedrive-pj
CRM Databases
hguareromanoo
F
license
Not graded
quality
D
maintenance
Read-only MCP server that exposes the Poli Júnior Pipedrive CRM to Claude as composable tools.
Updated 3 months ago (2026-06-12 02:44 UTC)
-
Uniware Vtiger MCP Server
CRM
Srimathi-8502
F
license
Not graded
quality
B
maintenance
Read-only MCP server connecting Claude to Vtiger CRM for leads, deals, and overdue follow-ups.
Updated a month ago (2026-08-17 11:05 UTC)
-
Telegram Lead Analysis MCP
Communication CRM
zeropennyads
F
license
Not graded
quality
C
maintenance
A read-only MCP server that exposes Telegram lead conversations to Claude for sales analysis, enabling lead summary, intent, stage, and follow-up insights.
Updated 3 months ago (2026-06-19 19:07 UTC)
-
firelever-mcpofficial
CRM Databases
firelever
F
license
Not graded
quality
B
maintenance
Read-only MCP server for querying the lead database and pipeline statistics.
Updated 2 months ago (2026-07-19 13:55 UTC)
-

BD CRM Analytics — MCP server

Tools

1. Prerequisites

2. Install & build

3. Mint a CRM Personal Access Token

4. Environment variables

5. Configure your MCP client

Cursor

Claude Desktop

Hosted service — web chat + remote MCP (server/)

Environment (hosted only)

Run locally

Connect Claude Desktop to the remote MCP endpoint

Deploy (reference — not auto-applied)

Behavior & troubleshooting

Development

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

firelever-mcpofficial

Hosted service — web chat + remote MCP (`server/`)