# io.github.cyanheads/reliefweb-mcp-server (remote · reliefweb.caseyjhand.com)

Search ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP.

- Trust score: 71/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `reliefweb.caseyjhand.com`: 71/100 (this document), [markdown](https://verifymcp.io/servers/cyanheads-reliefweb-mcp-server/reliefweb.md), [page](https://verifymcp.io/servers/cyanheads-reliefweb-mcp-server/reliefweb)
- npm · `@cyanheads/reliefweb-mcp-server`: 35/100, [markdown](https://verifymcp.io/servers/cyanheads-reliefweb-mcp-server/cyanheads-reliefweb-mcp-server.md), [page](https://verifymcp.io/servers/cyanheads-reliefweb-mcp-server/cyanheads-reliefweb-mcp-server)

## Channel facts

- Endpoint: `https://reliefweb.caseyjhand.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.14`

## 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 2026-08-03.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2574 tokens (~286/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http cyanheads-reliefweb-mcp-server https://reliefweb.caseyjhand.com/mcp
```

### Codex

```toml
[mcp_servers.cyanheads-reliefweb-mcp-server]
url = "https://reliefweb.caseyjhand.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cyanheads-reliefweb-mcp-server": {
      "type": "remote",
      "url": "https://reliefweb.caseyjhand.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cyanheads-reliefweb-mcp-server --url https://reliefweb.caseyjhand.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  cyanheads-reliefweb-mcp-server:
    url: "https://reliefweb.caseyjhand.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "cyanheads-reliefweb-mcp-server": {
      "type": "http",
      "url": "https://reliefweb.caseyjhand.com/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.

### 2026-08-03 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 68, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 68, +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.

### 2026-07-28 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 66, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 66)

First indexed and scored.

## MCP tools (9)

### `reliefweb_search_reports` (~614 tokens)

Search ReliefWeb Reports

Search humanitarian reports on ReliefWeb with filtering by country, disaster, format, theme, language, source, and date. Returns paginated summaries — use reliefweb_get_report to fetch full body text. Report body is excluded from results (10–100KB each); call get_report when document content is needed. Use preset include_archived=true to include expired or archived reports in historical research. Note: each call counts against the 1,000 calls/day quota.

Input parameters:

- `country` (string): ISO 3166-1 alpha-3 country code (e.g., SYR, AFG, UKR). Filters to content tagged with this country.
- `date_from` (string): Earliest publication date (ISO 8601, e.g., 2024-01-15T00:00:00+00:00). Filters on date.original (source publication date).
- `date_to` (string): Latest publication date (ISO 8601). Pair with date_from for a date range.
- `disaster_id` (integer): ReliefWeb numeric disaster ID. Filters to reports linked to a specific disaster. Get the ID from reliefweb_search_disasters.
- `filter` (object): Raw ReliefWeb filter object for compound conditions not covered by named params. Example: {"operator": "AND", "conditions": [{"field": "format.name", "value": "Map"}, {"field": "language.code", "valu…
- `format` (string): Content format filter. Valid values: Situation Report, Assessment, Analysis, Map, Infographic, Manual and Guideline, News and Press Release, Policy Document, Appeal, Financial Report, Evaluation and…
- `include_archived` (boolean): Include archived and to-review content in addition to published. Uses preset=analysis. Off by default.
- `language` (string): ISO 639-1 language code (e.g., en, fr, es, ar). Filters on language.code.
- `limit` (integer): Number of results to return (1–1000, default 10). Use a smaller value for targeted lookups; larger for bulk research. Each call counts against the 1,000-calls/day quota.
- `offset` (integer): Zero-based offset for pagination. Use with limit and the totalCount enrichment field to page through large result sets.
- `sort` (string): Sort order. Use date.original:desc for newest first (default), date.original:asc for oldest first, score:desc for relevance.
- `source` (string): Organization short name (e.g., UNHCR, OCHA, WFP). Filters on source.shortname.
- `text` (string): Full-text search query. Matches against title, body, and key metadata fields. Use plain natural language or keywords.
- `theme` (string): Sector or cross-cutting theme (e.g., Health, Food and Nutrition, Shelter and NFI, Protection). Matches theme.name.

Output parameters:

- `appliedFilters` (object): The resolved filter set the query actually ran with, after normalization and defaults. Echoes back so the agent can confirm how its inputs were interpreted.
- `items` (array): Matching reports (summaries only — use reliefweb_get_report for full body).
- `notice` (string): Recovery hint when results are empty — echoes the filters applied and suggests how to broaden. Absent on successful result pages.
- `totalCount` (number): Total reports matching the query before pagination.

### `reliefweb_get_report` (~96 tokens)

Get ReliefWeb Report

Fetch a single ReliefWeb report by its numeric ID with full body text, file attachments, and all metadata. Use after reliefweb_search_reports to retrieve document content — body is excluded from search results to manage context budget. Report bodies can be 10–100KB; call this only when you need the full document text.

Input parameters:

- `id` (integer, required): ReliefWeb numeric report ID. Obtained from reliefweb_search_reports results.

Output parameters:

- `body` (string): Full report body text (HTML). Present for most reports; absent for binary-only documents.
- `countries` (array): All countries tagged on this report.
- `dateCreated` (string): ReliefWeb index date (ISO 8601).
- `dateOriginal` (string): Source publication date (ISO 8601).
- `fileUrls` (array): Direct file download URLs attached to this report.
- `formats` (array): Content format names.
- `headlineSummary` (string): Short editorial summary from the headline block, when present.
- `id` (number): ReliefWeb numeric report ID.
- `languages` (array): Language codes (ISO 639-1).
- `primaryCountry` (string): Primary country name for this report.
- `sources` (array): Publishing organizations (short names).
- `themes` (array): Humanitarian theme/sector names.
- `title` (string): Report title.
- `urlAlias` (string): Canonical ReliefWeb URL for this report.

### `reliefweb_search_disasters` (~422 tokens)

Search ReliefWeb Disasters

Search active and historical disasters on ReliefWeb by type, country, status, date range, and GLIDE number. Default preset covers alert, current, and past disasters. Use include_archived=true to include alert-archive and archive entries for historical research. Returns IDs suitable for use with reliefweb_get_disaster and as disaster_id filter in reliefweb_search_reports.

Input parameters:

- `country` (string): ISO 3166-1 alpha-3 country code (e.g., SYR, AFG, UKR). Filters to disasters tagged with this country.
- `date_from` (string): Earliest disaster creation date (ISO 8601). Filters on date.created.
- `date_to` (string): Latest disaster creation date (ISO 8601). Pair with date_from for a date range.
- `disaster_type` (string): Disaster type name (e.g., Earthquake, Flood, Drought, Cyclone). Filters on type.name.
- `glide` (string): GLIDE number (global disaster identifier, e.g., EQ-2023-000053-TUR). Use for cross-system disaster correlation.
- `include_archived` (boolean): Include alert-archive and archive disasters in results. Uses preset=analysis. Off by default.
- `limit` (integer): Number of results to return (1–1000, default 10). Each call counts against the 1,000-calls/day quota.
- `offset` (integer): Zero-based offset for pagination. Use with limit and the totalCount enrichment field to page through results.
- `sort` (string): Sort order. Use date.created:desc for newest first (default), date.created:asc for oldest, score:desc for relevance.
- `status` (string): Disaster status filter. Values: alert (newly declared), current (ongoing), past (resolved), alert-archive, archive. Separate multiple values with commas. Default preset includes alert, current, past.
- `text` (string): Full-text search query. Matches against disaster name and description.

Output parameters:

- `appliedFilters` (object): The resolved filter set the query actually ran with, after normalization and defaults. Echoes back so the agent can confirm how its inputs were interpreted.
- `items` (array): Matching disasters.
- `notice` (string): Recovery hint when results are empty — echoes filters applied and suggests how to broaden.
- `totalCount` (number): Total disasters matching the query before pagination.

### `reliefweb_get_disaster` (~104 tokens)

Get ReliefWeb Disaster

Fetch a disaster record by ReliefWeb numeric ID including description, affected countries, GLIDE number, profile overview, key content links, and active appeals or response plans. Use after reliefweb_search_disasters to retrieve full details. Description and profile overview can together run to tens of KB for major disasters; call this only when you need the full narrative text.

Input parameters:

- `id` (integer, required): ReliefWeb numeric disaster ID. Obtained from reliefweb_search_disasters results.

Output parameters:

- `appealsResponsePlans` (array): Currently-active appeals and response plans linked to this disaster — the present set, not the full historical archive.
- `countries` (array): All countries tagged on this disaster.
- `dateCreated` (string): ReliefWeb index date (ISO 8601).
- `dateEvent` (string): Event date (ISO 8601), when available.
- `description` (string): Full disaster description text.
- `glide` (string): GLIDE number for cross-system correlation.
- `id` (number): ReliefWeb numeric disaster ID.
- `keyContent` (array): Currently-active curated key content links from the ReliefWeb editorial team — the present curated set, not the full historical archive.
- `name` (string): Disaster name.
- `primaryCountry` (string): Primary affected country.
- `primaryType` (string): Primary disaster type.
- `profileOverview` (string): Profile overview text from the ReliefWeb editorial team.
- `status` (string): Disaster status (alert, current, past, archive).
- `types` (array): Disaster type names.
- `urlAlias` (string): Canonical ReliefWeb URL for this disaster.
- `usefulLinks` (array): Currently-active useful external links curated by ReliefWeb editors — the present set, not the full historical archive.

### `reliefweb_get_country` (~103 tokens)

Get ReliefWeb Country Profile

Fetch a country profile from ReliefWeb by ISO3 code, including overview, humanitarian situation summary, key content links, active appeals and response plans, and useful external links. Country profiles are curated by OCHA editors and provide the authoritative situation summary for humanitarian responders.

Input parameters:

- `iso3` (string, required): ISO 3166-1 alpha-3 country code (e.g., SYR, AFG, UKR). Used to look up the country's ReliefWeb profile.

Output parameters:

- `appealsResponsePlans` (array): Currently-active humanitarian appeals and response plans for this country — the present set, not the full historical archive.
- `id` (number): ReliefWeb numeric country ID.
- `iso3` (string): ISO 3166-1 alpha-3 code.
- `keyContent` (array): Currently-active curated key content links maintained by ReliefWeb editors — the present curated set, not the full historical archive.
- `name` (string): Country name.
- `profileOverview` (string): Situation overview text from the ReliefWeb editorial team.
- `status` (string): Humanitarian situation status.
- `urlAlias` (string): Canonical ReliefWeb URL for this country page.
- `usefulLinks` (array): Currently-active useful external links curated by ReliefWeb editors — the present set, not the full historical archive.

### `reliefweb_list_countries` (~157 tokens)

List ReliefWeb Countries

List all countries and territories tracked by ReliefWeb, optionally filtered to active humanitarian situations. Returns ISO3 codes and status for each entry — use the ISO3 code with reliefweb_get_country to fetch a full profile. Set crisis_only=true to limit results to countries with active humanitarian situations.

Input parameters:

- `crisis_only` (boolean): When true, filters to countries with an active humanitarian situation (status ongoing). Default false returns all countries.
- `limit` (integer): Number of results to return (1–1000, default 100). Each call counts against the 1,000-calls/day quota.
- `offset` (integer): Zero-based offset for pagination. Use with limit and the totalCount enrichment field to page through results.

Output parameters:

- `items` (array): Countries tracked by ReliefWeb.
- `notice` (string): Recovery hint when results are empty — echoes the active filter and suggests how to broaden. Absent on successful result pages.
- `totalCount` (number): Total countries matching the filter before pagination.

### `reliefweb_search_jobs` (~345 tokens)

Search ReliefWeb Jobs

Search humanitarian job listings on ReliefWeb by country, organization, career category, theme, and experience level. Returns current open positions — archived or expired jobs are excluded by default. Use text search for role titles and job descriptions.

Input parameters:

- `career_category` (string): Humanitarian career track (e.g., Programme and Project Management, Information and Communications Technology, Logistics and Telecommunications). Filters on career_categories.name.
- `country` (string): ISO 3166-1 alpha-3 country code (e.g., SYR, AFG, UKR). Filters to jobs tagged with this country.
- `experience` (string): Experience level (e.g., 0-2 years, 3-4 years, 5-9 years). Filters on experience.name.
- `limit` (integer): Number of results to return (1–1000, default 10). Each call counts against the 1,000-calls/day quota.
- `offset` (integer): Zero-based offset for pagination. Use with limit and the totalCount enrichment field to page through results.
- `sort` (string): Sort order. Use date.created:desc for newest postings first (default), date.closing:asc to surface roles closing soonest, or score:desc for relevance.
- `source` (string): Organization short name (e.g., UNHCR, OCHA, WFP). Filters on source.shortname.
- `text` (string): Full-text search query. Matches against job title, body, and key metadata fields.
- `theme` (string): Sector or cross-cutting theme (e.g., Health, Food and Nutrition, Protection). Filters on theme.name.

Output parameters:

- `appliedFilters` (object): The resolved filter set the query actually ran with, after normalization and defaults. Echoes back so the agent can confirm how its inputs were interpreted.
- `items` (array): Matching job listings.
- `notice` (string): Recovery hint when results are empty — echoes filters applied and suggests how to broaden.
- `totalCount` (number): Total jobs matching the query before pagination.

### `reliefweb_search_training` (~417 tokens)

Search ReliefWeb Training

Search humanitarian training and learning opportunities on ReliefWeb by country, format, date, source, career category, and language. Covers on-site and online capacity-building events. Training date fields use date.start / date.end — different from report date fields. Use date_start_from and date_start_to to find upcoming training within a window. Results default to soonest-starting first (date.start:asc).

Input parameters:

- `career_category` (string): Humanitarian career track (e.g., Programme and Project Management, Information and Communications Technology). Filters on career_categories.name.
- `country` (string): ISO 3166-1 alpha-3 country code (e.g., KEN, ETH, COD). Filters to training tagged with this country.
- `date_start_from` (string): Training start date lower bound (ISO 8601). Filters on date.start — use to find training starting after a given date.
- `date_start_to` (string): Training start date upper bound (ISO 8601). Filters on date.start — pair with date_start_from for a window.
- `format` (string): Training format. Valid values: on-site, online. Filters on format.name.
- `language` (string): ISO 639-1 language code (e.g., en, fr, es). Filters on language.code.
- `limit` (integer): Number of results to return (1–1000, default 10). Each call counts against the 1,000-calls/day quota.
- `offset` (integer): Zero-based offset for pagination. Use with limit and the totalCount enrichment field to page through results.
- `sort` (string): Sort order. Use date.start:asc for soonest-starting training first (default), date.start:desc for latest-starting, date.created:desc for most recently posted, or score:desc for relevance.
- `source` (string): Organization short name. Filters on source.shortname.
- `text` (string): Full-text search query. Matches against training title and description.

Output parameters:

- `appliedFilters` (object): The resolved filter set the query actually ran with, after normalization and defaults. Echoes back so the agent can confirm how its inputs were interpreted.
- `items` (array): Matching training opportunities.
- `notice` (string): Recovery hint when results are empty — echoes filters applied and suggests how to broaden.
- `totalCount` (number): Total training listings matching the query before pagination.

### `reliefweb_list_sources` (~187 tokens)

List ReliefWeb Sources

Browse source organizations that contribute content to ReliefWeb, optionally filtered by name text or organization type. Returns short names, types, and URLs. Use the shortname value with the source filter in reliefweb_search_reports, reliefweb_search_jobs, and reliefweb_search_training.

Input parameters:

- `limit` (integer): Number of results to return (1–1000, default 10). Each call counts against the 1,000-calls/day quota.
- `offset` (integer): Zero-based offset for pagination. Use with limit and the totalCount enrichment field to page through results.
- `text` (string): Full-text search query. Matches against organization name and short name.
- `type` (string): Organization type. One of: Non-governmental Organization, International Organization, Academic and Research Institution, Other, Government, Media, Red Cross/Red Crescent Movement. Filters on type.nam…

Output parameters:

- `items` (array): Source organizations contributing content to ReliefWeb.
- `notice` (string): Recovery hint when results are empty — echoes the active filters and suggests how to broaden. Absent on successful result pages.
- `totalCount` (number): Total sources matching the query before pagination.

## Diagnostics

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

## Score history

- 2026-08-03: 71
- 2026-08-02: 70
- 2026-08-01: 70
- 2026-07-31: 69
- 2026-07-30: 68
- 2026-07-29: 68
- 2026-07-28: 67
- 2026-07-27: 66
- 2026-07-26: 66

## Links

- Remote endpoint: https://reliefweb.caseyjhand.com/mcp
- Repository: https://github.com/cyanheads/reliefweb-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/cyanheads-reliefweb-mcp-server/reliefweb/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/cyanheads-reliefweb-mcp-server/reliefweb/changelog.json
- HTML version of this page: https://verifymcp.io/servers/cyanheads-reliefweb-mcp-server/reliefweb