# welance/directory (remote · welance.com)

Match a project brief with small vetted software teams, anonymously; sign in to manage your own.

- Trust score: 72/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `welance.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/com-welance-directory/directory-mcp.md), [page](https://verifymcp.io/servers/com-welance-directory/directory-mcp)

## Channel facts

- Endpoint: `https://welance.com/directory/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2356 tokens (~117/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 75/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 24% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the welance/directory MCP server?

welance/directory is a hosted endpoint at https://welance.com/directory/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-welance-directory 'https://welance.com/directory/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-welance-directory": {
      "url": "https://welance.com/directory/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-welance-directory": {
      "type": "http",
      "url": "https://welance.com/directory/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-welance-directory]
url = "https://welance.com/directory/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-welance-directory": {
      "type": "remote",
      "url": "https://welance.com/directory/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-welance-directory --url 'https://welance.com/directory/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-welance-directory:
    url: "https://welance.com/directory/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-welance-directory": {
      "Transport": "http",
      "Url": "https://welance.com/directory/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-welance-directory -t streamable-http -u 'https://welance.com/directory/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-welance-directory": {
      "type": "http",
      "url": "https://welance.com/directory/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 68, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-27 (score 67)

First indexed and scored.

## MCP tools (20)

### `directory_capabilities` (~73 tokens)

What welance/directory is

What the directory is, who it is for (small vetted software teams for digital projects, especially ones rooted in the physical world), how pricing works (0% of the project; €30 + VAT from each side only to meet, charged once both accept a time), and the rule that the human stays the principal.

### `list_open_briefs` (~70 tokens)

Open briefs and delivered projects

The public briefs: open ones looking for a team, ones in vetting, and the archive of delivered projects with budget, sector and delivery team. Anonymised server-side. Filter by status or to tangible-world projects only.

Input parameters:

- `status` (string)
- `tangible` (boolean)

### `preview_teams` (~68 tokens)

A protected preview of the team board

Two anonymous, vetted teams as specimens (rotating daily) and the size of the supply — never the whole board. The board is brief-first: the teams that fit a project are listed only against a draft brief. Names and members are revealed only after a mutual €30-per-side handshake.

### `match_brief` (~118 tokens)

Shortlist teams for a draft brief

Match a draft brief (80–20000 characters) against the real, eligible anonymous teams: only teams the brief matches come back, with reasons and the defaults inferred from the brief. Same derivation and matcher as publishing, stores nothing, calls no LLM. Ends with a "Start this brief" link that opens the guided flow prefilled.

Input parameters:

- `brief` (string, required): The draft brief, markdown or plain text
- `language` (string): ISO 639-1 language the team must speak
- `title` (string)

### `brief_rules` (~37 tokens)

The public scoring rules

The rule catalogue a brief is scored against before teams see it: ids, labels, weights and the acceptance threshold that decides whether a brief publishes.

### `read_profile` (~34 tokens)

My profile

The signed-in person's own directory profile: job role, years of experience, languages, rated skills, hourly rate and verification state.

### `read_my_teams` (~95 tokens)

My teams

The signed-in person's teams: key (teamKey), name, and the facts the system derives rather than stores (members = confirmed people; rate = blended from members' rates unless the team sets an override; languages from members unless set); each team's profile (based, remote, availability, shipped work), open and matching brief counts, and a checklist of what pitching and the public board require, each marked met or missing.

### `read_my_pitches` (~43 tokens)

My briefs, pitches and bookings

The signed-in person's pitches and bookings on both sides: applications sent by their teams (with handshake and booking state) and the anonymous pitches received on their own briefs.

### `read_brief` (~34 tokens)

One brief

One public brief in full, markdown body included, by its id (briefId).

Input parameters:

- `briefId` (integer, required)

### `read_booking` (~42 tokens)

One booking

One booking by its id (bookingId): the proposed slots, its state, and which side the signed-in person is on.

Input parameters:

- `bookingId` (integer, required)

### `read_pitchable_briefs` (~43 tokens)

Briefs my teams can pitch on

For each of the signed-in person's teams, the open briefs that team can still pitch on: not yet pitched, pitch slots left, and a language match.

### `read_invoices` (~158 tokens)

My invoices

The signed-in person's past invoices with their PDF and document links (pdfUrl / documentUrl). Without filters it covers every billing identity of the person (personal VAT plus companies they own or administer); each invoice is tagged with its identity {kind, id, label, vatMasked}. identity ("all", "personal" or "org:<organisationId>") or identities (several of "personal" / "org:<organisationId>") narrow by identity; from/to (YYYY-MM-DD, inclusive) narrow by date; limit caps the count (1–50).

Input parameters:

- `from` (string)
- `identities` (array)
- `identity` (string)
- `limit` (integer)
- `to` (string)

### `propose_brief_draft` (~125 tokens)

Propose a brief draft

A proposed update to the person's local brief draft: title, markdown, and/or per-rule answers. Accepting it fills the brief editor; nothing is published. The whole proposal is limited to 64,000 UTF-8 bytes. Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `answers` (object)
- `markdown` (string)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.
- `title` (string)

### `propose_brief_publish` (~135 tokens)

Propose publishing a brief

A proposal to publish a brief (title, markdown, optional language) to the board. On confirmation the server's live score gate decides whether it publishes; publishing emails a one-time link and signs no one in. The whole proposal is limited to 64,000 UTF-8 bytes. Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `language` (string)
- `markdown` (string, required)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.
- `title` (string, required)

### `propose_profile_update` (~446 tokens)

Propose profile changes

Proposed field changes to one entity. entity "person": the signed-in person's own profile (job_role, years_experience, langs, skills, hourly_rate). entity "member" + teamKey + memberKey: a confirmed colleague on one of the person's teams (job_role, years_experience, langs, hourly_rate; skills are rated only by their owner). entity "team" + teamKey: intro, based, remote, availability, langs, shipped, hourly. entity "organisation" + organisationId: website, description of an organisation the person owns or administers (descriptive only; it verifies nothing). Skills: changes[{field:"skills", value:[{name, rating 1–10}]}] adds or re-rates (an existing name takes the new rating); removeSkills lists skill names to remove. Languages: addLangs / removeLangs take two-letter codes; alternatively a langs change carries the complete new list (not both). Scalars: changes[{field, value}]; hourly_rate is EUR/h, 10–2000; team hourly overrides the rate blended from members' rates, and null restores the blend; team size is not a field (it is the confirmed member count). Team shipped: value lists entries to add, each {title, url, desc}; existing entries are kept; removeShipped lists titles or links to remove. inferred=true marks a value derived from evidence rather than stated by the person; hourly rate, availability, languages and skill ratings are rejected when inferred. Each changed field becomes a separate card the person approves. Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `addLangs` (array)
- `changes` (array)
- `entity` (string, required)
- `memberKey` (string)
- `organisationId` (string)
- `removeLangs` (array)
- `removeShipped` (array)
- `removeSkills` (array)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.
- `teamKey` (string)

### `propose_team_invite` (~132 tokens)

Propose inviting someone to a team

A proposal to invite a person to one of the signed-in person's teams (teamKey) by name and email, with an optional role. Once confirmed, the invitee receives an email; their skill ratings are theirs to set later. Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `email` (string, required)
- `name` (string, required)
- `role` (string)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.
- `teamKey` (string, required)

### `propose_pitch_draft` (~125 tokens)

Propose a pitch draft

An anonymous pitch draft for one of the person's teams (teamKey) on an open brief (briefId). Accepting it fills the existing pitch editor; nothing is sent. Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `briefId` (integer, required)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.
- `teamKey` (string, required)
- `text` (string, required): Anonymous: no names, emails, phone numbers or links.

### `propose_pitch_send` (~134 tokens)

Propose sending a pitch

A proposal to send an anonymous pitch for one of the person's teams (teamKey) on an open brief (briefId); once confirmed, the brief owner sees it. Each brief accepts a limited number of pitches (10). Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `briefId` (integer, required)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.
- `teamKey` (string, required)
- `text` (string, required): Anonymous: no names, emails, phone numbers or links.

### `propose_booking` (~179 tokens)

Propose meeting times

As the client of a pitch on the person's own brief (appId): a proposed 30-minute call with at least 3 concrete slots (ISO 8601; weekdays, on the hour, 09–18 CET, 3–10 business days ahead) and an optional note. Confirming holds €30 from the client's side for up to 7 days; nothing is charged until both sides accept a time. A no-show's €30 is not returned; the side that showed gets a credit. Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `appId` (integer, required)
- `note` (string)
- `slots` (array, required)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.

### `propose_booking_accept` (~133 tokens)

Propose accepting a meeting time

As the team on a booking (bookingId): a proposal to accept one of the client's offered slots (slotId). Accepting charges €30 from each side; if the client does not show, the team's €30 becomes a credit; if the team does not show, its €30 is not returned. Stores a proposal only. Nothing happens until the person confirms it on welance.com/directory; the result includes the review link.

Input parameters:

- `bookingId` (integer, required)
- `slotId` (integer, required)
- `summary` (string, required): One sentence, in the conversation language, saying what happens on confirm.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-welance-directory/directory-mcp#diagnostics

## Score history

- 2026-11-05: 72
- 2026-11-04: 71
- 2026-11-03: 71
- 2026-11-02: 70
- 2026-11-01: 70
- 2026-10-31: 69
- 2026-10-30: 69
- 2026-10-29: 68
- 2026-10-28: 68
- 2026-10-27: 67

## Common questions

### What is the welance/directory MCP server?

welance/directory is an MCP server listed in the public MCP registry as com.welance/directory. Match a project brief with small vetted software teams, anonymously; sign in to manage your own. This page covers its hosted endpoint (https://welance.com/directory/mcp).

### Is the welance/directory MCP server safe to use?

welance/directory scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the welance/directory MCP server expose?

welance/directory exposes 20 tools: directory_capabilities, list_open_briefs, preview_teams, match_brief, brief_rules, and 15 more. Their descriptions and schemas cost roughly 2,224 tokens of context every time the server is loaded.

### Does the welance/directory MCP server require authentication?

No. We connected to welance/directory without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the welance/directory MCP server still maintained?

welance/directory is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://welance.com/directory/mcp
- Website: https://welance.com/directory/connect
- Changelog RSS feed: https://verifymcp.io/servers/com-welance-directory/directory-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-welance-directory/directory-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-welance-directory/directory-mcp