Pharma Intel

Pharma Pipeline Scan

pharma_pipeline_scan

Read-onlyIdempotent

Search clinical trials by condition (e.g., "lung cancer") or sponsor (e.g., "Pfizer"). Returns trial phases, recruitment status, and approved treatments for that indication. Pass status and phase together to answer combined questions like "how many Phase 3 obesity trials are recruiting" with the true intersection count plus a lead-sponsor tally.

Input Schema

TableJSON Schema

Name	Required	Description
`phase`	No	Trial phase filter applied to every count and the study list: PHASE1, PHASE2, PHASE3, or PHASE4.
`status`	No	Recruitment status filter applied to every count and the study list: RECRUITING, ACTIVE_NOT_RECRUITING, COMPLETED, etc.
`sponsor`	No	Pharmaceutical company or sponsor name
`condition`	No	Disease or condition (e.g., "breast cancer")

Output Schema

TableJSON Schema

Name	Required	Description
`sponsor`	No	Sponsor name when sponsor-focused search
`analysis`	Yes	Analysis type identifier
`condition`	No	Condition name when condition-focused search
`all_trials`	No	All trials for sponsor
`approved_drugs`	No	FDA approved drugs for condition
`recent_updates`	No	Recent trial updates
`recruiting_trials`	No	Recruiting trials for condition
`total_trial_counts`	No	Trial counts by condition
`recruiting_by_phase`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed3 schema fields changedAug 18, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "condition": "lung cancer"
-  },
-  {
-    "sponsor": "Pfizer"
-  },
-  {
-    "condition": "breast cancer",
-    "sponsor": "Moderna"
-  }
-]New value: +[
+  {
+    "condition": "lung cancer"
+  },
+  {
+    "sponsor": "Pfizer"
+  },
+  {
+    "condition": "obesity",
+    "phase": "PHASE3",
+    "status": "RECRUITING"
+  },
+  {
+    "condition": "breast cancer",
+    "sponsor": "Moderna"
+  }
+]

addedInput schema / properties / phase

Added value: +{
+  "description": "Trial phase filter applied to every count and the study list: PHASE1, PHASE2, PHASE3, or PHASE4.",
+  "type": "string"
+}

addedInput schema / properties / status

Added value: +{
+  "description": "Recruitment status filter applied to every count and the study list: RECRUITING, ACTIVE_NOT_RECRUITING, COMPLETED, etc.",
+  "type": "string"
+}

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "all_trials": {
+      "description": "All trials for sponsor",
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "analysis": {
+      "description": "Analysis type identifier",
+      "enum": [
+        "pipeline_scan"
+      ],
+      "type": "string"
+    },
+    "approved_drugs": {
+      "description": "FDA approved drugs for condition",
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "condition": {
+      "description": "Condition name when condition-focused search",
+      "type": "string"
+    },
+    "recent_updates": {
+      "description": "Recent trial updates",
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "recruiting_by_phase": {
+      "properties": {
+        "phase1": {
+          "description": "Phase 1 recruiting trials",
+          "type": [
+            "object",
+            "null"
+          ]
+        },
+        "phase2": {
+          "description": "Phase 2 recruiting trials",
+          "type": [
+            "object",
+            "null"
+          ]
+        },
+        "phase3": {
+          "description": "Phase 3 recruiting trials",
+          "type": [
+            "object",
+            "null"
+          ]
+        }
+      },
+      "type": "object"
+    },
+    "recruiting_trials": {
+      "description": "Recruiting trials for condition",
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "sponsor": {
+      "description": "Sponsor name when sponsor-focused search",
+      "type": "string"
+    },
+    "total_trial_counts": {
+      "description": "Trial counts by condition",
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "analysis"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "condition": "lung cancer"
+  },
+  {
+    "sponsor": "Pfizer"
+  },
+  {
+    "condition": "breast cancer",
+    "sponsor": "Moderna"
+  }
+]

First observedApr 22, 2026

TDQS

A3.9/5.0

Behavior4/5

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

The annotations already declare the tool is read-only, idempotent, and non-destructive. The description adds value by revealing the combined query behavior (true intersection count plus lead-sponsor tally) and the general output contents (phases, status, approvals). There is no contradiction with the annotations.

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 three sentences with no unnecessary words. The first sentence states the primary function. The second lists what is returned. The third gives a specific combined-parameter example. Every sentence earns its place, and the structure is front-loaded for quick scanning.

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 rich annotations and presence of an output schema, the description covers the essential behavioral aspects: search capability, output summary, and special combined-parameter handling. It does not discuss pagination, limits, or format details, but the output schema likely covers that, so completeness is adequate.

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% with each parameter described individually. The description goes further by explaining how using status and phase together changes the output semantics (intersection count, tally). This interaction-level detail is not present in the schema and improves the agent's understanding of combined parameter use.

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

Purpose4/5

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

The description clearly states the tool searches clinical trials by condition or sponsor and returns phases, statuses, and approved treatments. However, it does not explicitly differentiate from sibling tools like pharma_pipeline_catalysts or pharma_indication_landscape, which could cause ambiguity for an agent deciding between them.

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 provides a concrete usage example for combined status and phase queries, explaining the special intersection + tally behavior. However, it offers no guidance on when to avoid this tool in favor of siblings (e.g., when a deep drug profile is needed) or when to use only condition vs. sponsor. The guidance is implicit rather than explicit.

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

All Pharma Intel tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose, even within the same domain (e.g., ask_pipeworx vs ask_pipeworx_grounded vs ask_pipeworx_beta are differentiated by groundedness/beta status; polymarket_edges vs polymarket_arbitrage vs polymarket_fill_risk each target discovery vs arbitrage vs execution risk). The descriptions are highly detailed, eliminating ambiguity about when to use each.

Naming Consistency4/5

All tool names use snake_case consistently, and most follow a verb-first pattern (ask_, compare_, discover_, search_, validate_), but a few are noun-first (entity_profile, polymarket_edges, recent_alerts). The style is readable and predictable, though not perfectly uniform in the verb_noun convention.

Tool Count2/5

With 37 tools, the server is heavily over-scoped, especially given the 'Pharma Intel' name that suggests a focused pharma domain. Many tools are general-purpose (prediction markets, memory, subscription management, feedback) unrelated to the server's apparent purpose, making it feel like a grab bag rather than a cohesive set.

Completeness4/5

The pharma-specific tools cover drug profiles, safety, pipeline scans, catalysts, indication landscapes, and sponsor diligence – a solid lifecycle coverage. The broader data/query/prediction-market tools also feel complete for their respective sub-domains. The only minor gaps are niche operations (e.g., updating a subscription), but these are not critical to the core workflows.

Resources

Need Help?