Skip to main content
Glama
Sign In

reliefweb-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Search ReliefWeb Jobs

reliefweb_search_jobs
Read-onlyIdempotent

Search humanitarian job listings on ReliefWeb by country, organization, career category, theme, and experience level. Returns current open positions — expired postings are excluded by default. Use include_archived=true to search the full history of postings, which is far larger than the open set. Use text search for role titles and job descriptions.

Input Schema

NameRequiredDescriptionDefault
sortNoSort order. Use date.created:desc for newest postings first (default), date.closing:asc to surface roles closing soonest, or score:desc for relevance.
textNoFull-text search query. Matches against job title, body, and key metadata fields.
limitNoNumber of results to return (1–1000, default 10). Larger integers are clamped to 1000 with a notice when clamping is enabled; otherwise they are rejected. Each call counts against the 1,000-calls/day quota.
themeNoSector or cross-cutting theme (e.g., Health, Food and Nutrition, Protection). Filters on theme.name.
offsetNoZero-based offset for pagination. Use with limit and the totalCount enrichment field to page through results.
sourceNoOrganization short name (e.g., UNHCR, OCHA, WFP). Filters on source.shortname.
countryNoISO 3166-1 alpha-3 country code (e.g., SYR, AFG, UKR). Filters to jobs tagged with this country.
experienceNoExperience level (e.g., 0-2 years, 3-4 years, 5-9 years). Filters on experience.name.
career_categoryNoReliefWeb career-category name (e.g., Program/Project Management, Information and Communications Technology, Logistics/Procurement). Filters on career_categories.name.
include_archivedNoSearch expired postings alongside the open ones. Uses preset=analysis. Off by default — the open set is a small fraction of the archive, so turn this on for labour-market history rather than for a hiring snapshot.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
itemsNoMatching job listings.
noticeNoDiscloses requested and applied limits when clamped. For empty pages, names the match count and last reachable offset when records matched; otherwise echoes filters and suggests how to broaden.
totalCountNoTotal jobs matching the query before pagination.
appliedFiltersNoThe resolved filter set the query actually ran with, after normalization and defaults. Echoes back so the agent can confirm how its inputs were interpreted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / career_category / description
      Previous value: -"Humanitarian career track (e.g., Programme and Project Management, Information and Communications Technology, Logistics and Telecommunications). Filters on career_categories.name."New value: +"ReliefWeb career-category name (e.g., Program/Project Management, Information and Communications Technology, Logistics/Procurement). Filters on career_categories.name."
    • changedInput schema / properties / limit / description
      Previous value: -"Number of results to return (1–1000, default 10). Each call counts against the 1,000-calls/day quota."New value: +"Number of results to return (1–1000, default 10). Larger integers are clamped to 1000 with a notice when clamping is enabled; otherwise they are rejected. Each call counts against the 1,000-calls/day quota."
    • changedInput schema / properties / limit / maximum
      Previous value: -1000New value: +9007199254740991
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_query`: ReliefWeb rejected the query — typically an unrecognized sort field. `upstream_error`: The ReliefWeb API was unreachable, timed out, or returned a server error. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_query`: ReliefWeb rejected the query — possible causes include malformed text or an unrecognized sort field. `upstream_error`: The ReliefWeb API was unreachable, timed out, or returned a server error. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / notice / description
      Previous value: -"Present only when the page is empty. Names the match count and the last reachable offset when the query matched records; otherwise echoes the filters applied and suggests how to broaden."New value: +"Discloses requested and applied limits when clamped. For empty pages, names the match count and last reachable offset when records matched; otherwise echoes filters and suggests how to broaden."
  2. Changed6 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedOutput schema / anyOf
      Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "items",
+      "appliedFilters",
+      "totalCount"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]
    • addedOutput schema / properties / error
      Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `invalid_query`: ReliefWeb rejected the query — typically an unrecognized sort field. `upstream_error`: The ReliefWeb API was unreachable, timed out, or returned a server error. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "invalid_query",
+            "upstream_error"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}
    • removedOutput schema / required
      Removed value: -[
-  "items",
-  "appliedFilters",
-  "totalCount"
-]
  3. Changed3 schema fields changed
    • addedInput schema / properties / include_archived
      Added value: +{
+  "description": "Search expired postings alongside the open ones. Uses preset=analysis. Off by default — the open set is a small fraction of the archive, so turn this on for labour-market history rather than for a hiring snapshot.",
+  "type": "boolean"
+}
    • addedOutput schema / properties / appliedFilters / properties / preset
      Added value: +{
+  "description": "ReliefWeb preset the query used: latest (open postings only, default) or analysis when include_archived.",
+  "type": "string"
+}
    • changedOutput schema / properties / appliedFilters / required
      Previous value: -[
-  "sort",
-  "limit",
-  "offset"
-]New value: +[
+  "sort",
+  "preset",
+  "limit",
+  "offset"
+]
  4. Changed1 schema field changed
    • changedOutput schema / properties / notice / description
      Previous value: -"Recovery hint when results are empty — echoes filters applied and suggests how to broaden."New value: +"Present only when the page is empty. Names the match count and the last reachable offset when the query matched records; otherwise echoes the filters applied and suggests how to broaden."
  5. Changed1 schema field changed
    • addedInput schema / properties / sort
      Added value: +{
+  "description": "Sort order. Use date.created:desc for newest postings first (default), date.closing:asc to surface roles closing soonest, or score:desc for relevance.",
+  "type": "string"
+}
  6. Changed2 schema fields changed
    • addedOutput schema / properties / appliedFilters
      Added value: +{
+  "additionalProperties": false,
+  "description": "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.",
+  "properties": {
+    "careerCategory": {
+      "description": "Career category name filter applied.",
+      "type": "string"
+    },
+    "country": {
+      "description": "Country code as normalized (uppercased ISO3).",
+      "type": "string"
+    },
+    "experience": {
+      "description": "Experience level filter applied.",
+      "type": "string"
+    },
+    "limit": {
+      "description": "Result limit the query used.",
+      "type": "number"
+    },
+    "offset": {
+      "description": "Pagination offset the query used.",
+      "type": "number"
+    },
+    "sort": {
+      "description": "Sort order the query used (resolved, including the default).",
+      "type": "string"
+    },
+    "source": {
+      "description": "Source short name filter applied.",
+      "type": "string"
+    },
+    "text": {
+      "description": "Full-text query the search used.",
+      "type": "string"
+    },
+    "theme": {
+      "description": "Theme name filter applied.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "sort",
+    "limit",
+    "offset"
+  ],
+  "type": "object"
+}
    • changedOutput schema / required
      Previous value: -[
-  "items",
-  "totalCount"
-]New value: +[
+  "items",
+  "appliedFilters",
+  "totalCount"
+]
  7. Changed3 schema fields changed
    • changedInput schema / properties / offset / description
      Previous value: -"Zero-based offset for pagination. Use with limit and totalCount to page through results."New value: +"Zero-based offset for pagination. Use with limit and the totalCount enrichment field to page through results."
    • removedOutput schema / properties / message
      Removed value: -{
-  "description": "Recovery hint when results are empty — echoes filters applied and suggests how to broaden.",
-  "type": "string"
-}
    • addedOutput schema / properties / notice
      Added value: +{
+  "description": "Recovery hint when results are empty — echoes filters applied and suggests how to broaden.",
+  "type": "string"
+}
  8. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, open-world reads, so the description's job is to add scope semantics — and it does: expired postings are excluded by default, and the archive is described as "far larger" than the open set, a real behavioral tradeoff. It does not mention rate limits in the prose (that lives only in the limit param), keeping it just short of a 5.

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?

Four sentences, front-loaded with purpose, then the default scope, then the archive override, then the text-search hint. No filler and no repetition of annotation content.

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

Completeness5/5

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

For a 10-parameter search tool with an output schema and full schema coverage, the description supplies exactly the missing piece — what the default result set actually contains and when to widen it. Return format is correctly left to the output schema.

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 description coverage is 100%, so the baseline is 3 — every parameter including sort, country and experience is already documented in the schema. The description restates the filter set and adds a light heuristic for `text`, but contributes no syntax or format detail beyond the structured fields.

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?

States a specific verb and resource ("Search humanitarian job listings on ReliefWeb") and enumerates the filter dimensions, which immediately separates it from reliefweb_get_job (single-record fetch). An agent can identify the correct tool without opening the schema.

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?

Clearly explains the key branching decision — default open-postings scope vs. include_archived=true for labour-market history — and points text search at role titles/descriptions. It stops short of naming sibling tools (e.g., reliefweb_get_job for a known posting ID), so it is strong but not fully alternative-aware.

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

All reliefweb-mcp-server toolsInspect
Try in Browser
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

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources