pubchem-mcp-server

Get Bioactivity

pubchem_get_bioactivity

Read-onlyIdempotent

Retrieve a compound's bioactivity profile from PubChem, including assay outcomes, targets, and IC50/EC50/Ki values. Filter by active/inactive outcome or specific gene/protein target.

Instructions

Get a compound's bioactivity profile: which assays tested it, activity outcomes (Active/Inactive/Inconclusive), target identifiers (NCBI Gene ID, UniProt/GenBank accession), and quantitative values (IC50, EC50, Ki, etc.). Filter by outcome and/or a specific molecular target (NCBI Gene ID or protein accession) to focus the profile — e.g. "is this compound active against target T?".

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cid`	Yes	PubChem Compound ID. Resolve from name/SMILES with pubchem_search_compounds.
`offset`	No	Zero-based index of the first assay to return, applied after the outcome and target filters. Pass the nextOffset from a previous call to read the following page. Default: 0.
`maxResults`	No	Max assay results to return per page. The per-call cap is 100: a larger value (up to 1000) returns a page of 100 and is reported in cappedInputs. Well-studied compounds have thousands of records; use offset to reach the ones past this page. Default: 20.
`targetGeneId`	No	Filter to assays against this NCBI Gene ID (1 to 2147483647), including assays recorded only under a protein accession this compound's assay table pairs with the Gene ID (e.g. 5742 also reaches rows carrying only P23219 when another row pairs the two). Obtain Gene IDs from pubchem_search_assays or the targetGeneId field of an unfiltered result here. Combine with outcomeFilter="active" to answer "is this compound active against target T?".
`outcomeFilter`	No	Filter by activity outcome against each assay's reported target: the target a target filter matched, else the first target the assay lists. For a multi-target assay, outcomes against its other targets (in otherTargets) do not count. "active" keeps assays where that outcome is Active — most useful for understanding biological profile. Default: "all".	all
`targetAccession`	No	Filter to assays against this target protein accession (UniProt/RefSeq/GenBank/PDB chain), e.g. "P35354", including assays recorded only under a Gene ID or another accession this compound's assay table pairs with it. Uppercased before matching; a PDB chain ID (the "A" in "1ZHH_A") is kept as given. With targetGeneId, both must name the same target — when the table ties them to different targets, nothing matches. Obtain accessions from pubchem_search_assays or the targetAccession field of an unfiltered result here.

Output Schema

TableJSON Schema

Name	Required	Description
`cap`	No	The page size applied: maxResults, or the per-call cap when maxResults exceeds it.
`cid`	No	PubChem Compound ID.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Assays returned on this page.
`notice`	No	Recovery guidance when the filter yields no results or the compound has no bioactivity data.
`offset`	No	Zero-based index of the first assay returned.
`results`	No	Assay results matching the filter.
`truncated`	No	True when matching assays remain past this page.
`nextOffset`	No	Offset to pass on the next call to continue past this page. Omitted when no further assays match.
`activeCount`	No	Assays whose outcome against their first listed target is "Active", across all assays and before any filter. A multi-target assay counts by its first target only.
`totalAssays`	No	Total unique assays for this compound.
`cappedInputs`	No	Inputs that asked for more than their per-call cap, with the value requested and the value served. An ID batch lists the IDs past the cap in unprocessed. Omitted when every input was within its cap.
`targetFilter`	No	Target identifiers matched, when a target filter is set: those passed plus every Gene ID and accession the compound's assay table pairs with them. When the two inputs name different targets, only the two inputs.
`filteredCount`	No	Exact number of assays matching the outcome and target filters, across all pages.
`inactiveCount`	No	Assays whose outcome against their first listed target is "Inactive", across all assays and before any filter. A multi-target assay counts by its first target only.
`outcomeFilter`	No	Outcome filter applied: active, inactive, or all.
`returnedCount`	No	Assays returned on this page.

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedv0.7.0Oct 16, 2026

changedInput schema / properties / cid / maximum

Previous value: -9007199254740991New value: +2147483647

changedInput schema / properties / maxResults / description

Previous value: -"Max assay results to return per page (1-100). Well-studied compounds have thousands of records; use offset to reach the ones past this page. Default: 20."New value: +"Max assay results to return per page. The per-call cap is 100: a larger value (up to 1000) returns a page of 100 and is reported in cappedInputs. Well-studied compounds have thousands of records; use offset to reach the ones past this page. Default: 20."

changedInput schema / properties / maxResults / maximum
```
Previous value: -100New value: +1000
```

changedInput schema / properties / outcomeFilter / description

Previous value: -"Filter by activity outcome. \"active\" shows only assays where the compound showed activity — most useful for understanding biological profile. Default: \"all\"."New value: +"Filter by activity outcome against each assay's reported target: the target a target filter matched, else the first target the assay lists. For a multi-target assay, outcomes against its other targets (in otherTargets) do not count. \"active\" keeps assays where that outcome is Active — most useful for understanding biological profile. Default: \"all\"."

changedInput schema / properties / targetAccession / description

Previous value: -"Filter to assays against this target protein accession (UniProt/GenBank), e.g. \"P35354\". Obtain accessions from pubchem_search_assays or the targetAccession field of an unfiltered result here."New value: +"Filter to assays against this target protein accession (UniProt/RefSeq/GenBank/PDB chain), e.g. \"P35354\", including assays recorded only under a Gene ID or another accession this compound's assay table pairs with it. Uppercased before matching; a PDB chain ID (the \"A\" in \"1ZHH_A\") is kept as given. With targetGeneId, both must name the same target — when the table ties them to different targets, nothing matches. Obtain accessions from pubchem_search_assays or the targetAccession field of an unfiltered result here."

changedInput schema / properties / targetGeneId / description

Previous value: -"Filter to assays against this NCBI Gene ID. Obtain Gene IDs from pubchem_search_assays or the targetGeneId field of an unfiltered result here. Combine with outcomeFilter=\"active\" to answer \"is this compound active against target T?\"."New value: +"Filter to assays against this NCBI Gene ID (1 to 2147483647), including assays recorded only under a protein accession this compound's assay table pairs with the Gene ID (e.g. 5742 also reaches rows carrying only P23219 when another row pairs the two). Obtain Gene IDs from pubchem_search_assays or the targetGeneId field of an unfiltered result here. Combine with outcomeFilter=\"active\" to answer \"is this compound active against target T?\"."

changedInput schema / properties / targetGeneId / maximum

Previous value: -9007199254740991New value: +2147483647

changedOutput schema / properties / activeCount / description

Previous value: -"Assays with \"Active\" outcome."New value: +"Assays whose outcome against their first listed target is \"Active\", across all assays and before any filter. A multi-target assay counts by its first target only."

changedOutput schema / properties / cap / description

Previous value: -"The maxResults cap that was applied."New value: +"The page size applied: maxResults, or the per-call cap when maxResults exceeds it."

addedOutput schema / properties / cappedInputs

Added value: +{
+  "description": "Inputs that asked for more than their per-call cap, with the value requested and the value served. An ID batch lists the IDs past the cap in unprocessed. Omitted when every input was within its cap.",
+  "items": {
+    "additionalProperties": false,
+    "description": "One input served at its per-call cap.",
+    "properties": {
+      "input": {
+        "description": "Input name, e.g. \"maxResults\" or \"cids\".",
+        "type": "string"
+      },
+      "requested": {
+        "description": "Value requested: the page size, or the number of IDs in the batch.",
+        "type": "number"
+      },
+      "served": {
+        "description": "Value served: the per-call cap.",
+        "type": "number"
+      },
+      "unprocessed": {
+        "description": "ID batches only: IDs past the cap, listed in unprocessed in input order.",
+        "type": "number"
+      }
+    },
+    "required": [
+      "input",
+      "requested",
+      "served"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / properties / inactiveCount / description

Previous value: -"Assays with \"Inactive\" outcome."New value: +"Assays whose outcome against their first listed target is \"Inactive\", across all assays and before any filter. A multi-target assay counts by its first target only."

changedOutput schema / properties / results / items / properties / activityValues / description

Previous value: -"Quantitative activity measurements."New value: +"Quantitative activity measurements against the reported target."

addedOutput schema / properties / results / items / properties / otherTargets

Added value: +{
+  "description": "The assay's other targets, each with its own outcome and measurements. Present only for an assay whose rows name more than one target.",
+  "items": {
+    "additionalProperties": false,
+    "description": "Another target of the assay, with its own outcome and values.",
+    "properties": {
+      "accession": {
+        "description": "Protein accession. Omitted when the row names none.",
+        "type": "string"
+      },
+      "activityValues": {
+        "description": "Quantitative activity measurements against this target.",
+        "items": {
+          "additionalProperties": false,
+          "description": "Quantitative activity measurement entry.",
+          "properties": {
+            "name": {
+              "description": "Measurement name (e.g. IC50, EC50, Ki). Omitted when not reported.",
+              "type": "string"
+            },
+            "unit": {
+              "description": "Unit of measurement (e.g. uM, nM). Omitted when not reported.",
+              "type": "string"
+            },
+            "value": {
+              "description": "Measured value.",
+              "type": "number"
+            }
+          },
+          "required": [
+            "value"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "geneId": {
+        "description": "NCBI Gene ID. Omitted when the row names none.",
+        "type": "number"
+      },
+      "outcome": {
+        "description": "Activity outcome against this target.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "outcome",
+      "activityValues"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / properties / results / items / properties / outcome / description

Previous value: -"Activity outcome: Active, Inactive, Inconclusive, Unspecified."New value: +"Activity outcome against the reported target — the one a target filter matched, else the assay's first: Active, Inactive, Inconclusive, Unspecified."

changedOutput schema / properties / results / items / properties / targetAccession / description

Previous value: -"Target protein accession (UniProt/GenBank)."New value: +"Reported target's protein accession (UniProt/RefSeq/GenBank/PDB chain)."

changedOutput schema / properties / results / items / properties / targetGeneId / description
```
Previous value: -"Target NCBI Gene ID."New value: +"Reported target's NCBI Gene ID."
```

changedOutput schema / properties / targetFilter / description

Previous value: -"Target filter applied (gene ID and/or protein accession), when set."New value: +"Target identifiers matched, when a target filter is set: those passed plus every Gene ID and accession the compound's assay table pairs with them. When the two inputs name different targets, only the two inputs."

Changed4 schema fields changedv0.6.5Sep 25, 2026
- removedInput schema / properties / cid / exclusiveMinimum
```
Removed value: -0
```
- addedInput schema / properties / cid / minimum
```
Added value: +1
```
- removedInput schema / properties / targetGeneId / exclusiveMinimum
```
Removed value: -0
```
- addedInput schema / properties / targetGeneId / minimum
```
Added value: +1
```

Changed6 schema fields changedv0.6.1Aug 28, 2026

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": [
+      "cid",
+      "totalAssays",
+      "activeCount",
+      "inactiveCount",
+      "results",
+      "outcomeFilter",
+      "filteredCount",
+      "returnedCount",
+      "offset"
+    ]
+  },
+  {
+    "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.",
+          "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: -[
-  "cid",
-  "totalAssays",
-  "activeCount",
-  "inactiveCount",
-  "results",
-  "outcomeFilter",
-  "filteredCount",
-  "returnedCount",
-  "offset"
-]

Changed10 schema fields changedv0.6.0Jul 30, 2026

changedInput schema / properties / maxResults / description

Previous value: -"Max assay results to return (1-100). Well-studied compounds have thousands of records. Default: 20."New value: +"Max assay results to return per page (1-100). Well-studied compounds have thousands of records; use offset to reach the ones past this page. Default: 20."

changedInput schema / properties / maxResults / type
```
Previous value: -"number"New value: +"integer"
```

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Zero-based index of the first assay to return, applied after the outcome and target filters. Pass the nextOffset from a previous call to read the following page. Default: 0.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

changedOutput schema / properties / filteredCount / description

Previous value: -"Assays matching the outcome and target filters, before the maxResults cap."New value: +"Exact number of assays matching the outcome and target filters, across all pages."

addedOutput schema / properties / nextOffset

Added value: +{
+  "description": "Offset to pass on the next call to continue past this page. Omitted when no further assays match.",
+  "type": "number"
+}

addedOutput schema / properties / offset

Added value: +{
+  "description": "Zero-based index of the first assay returned.",
+  "type": "number"
+}

changedOutput schema / properties / returnedCount / description

Previous value: -"Assays returned after the maxResults cap."New value: +"Assays returned on this page."

changedOutput schema / properties / shown / description

Previous value: -"Assays returned after the maxResults cap."New value: +"Assays returned on this page."

changedOutput schema / properties / truncated / description

Previous value: -"True when results were capped at maxResults — more matching assays exist."New value: +"True when matching assays remain past this page."

changedOutput schema / required

Previous value: -[
-  "cid",
-  "totalAssays",
-  "activeCount",
-  "inactiveCount",
-  "results",
-  "outcomeFilter",
-  "filteredCount",
-  "returnedCount"
-]New value: +[
+  "cid",
+  "totalAssays",
+  "activeCount",
+  "inactiveCount",
+  "results",
+  "outcomeFilter",
+  "filteredCount",
+  "returnedCount",
+  "offset"
+]

Changed3 schema fields changedv0.2.4Jun 21, 2026

addedOutput schema / properties / cap

Added value: +{
+  "description": "The maxResults cap that was applied.",
+  "type": "number"
+}

addedOutput schema / properties / shown

Added value: +{
+  "description": "Assays returned after the maxResults cap.",
+  "type": "number"
+}

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when results were capped at maxResults — more matching assays exist.",
+  "type": "boolean"
+}

Changed8 schema fields changedv0.2.2Jun 4, 2026

addedInput schema / properties / targetAccession

Added value: +{
+  "description": "Filter to assays against this target protein accession (UniProt/GenBank), e.g. \"P35354\". Obtain accessions from pubchem_search_assays or the targetAccession field of an unfiltered result here.",
+  "type": "string"
+}

addedInput schema / properties / targetGeneId

Added value: +{
+  "description": "Filter to assays against this NCBI Gene ID. Obtain Gene IDs from pubchem_search_assays or the targetGeneId field of an unfiltered result here. Combine with outcomeFilter=\"active\" to answer \"is this compound active against target T?\".",
+  "exclusiveMinimum": 0,
+  "maximum": 9007199254740991,
+  "type": "integer"
+}

addedOutput schema / properties / filteredCount

Added value: +{
+  "description": "Assays matching the outcome and target filters, before the maxResults cap.",
+  "type": "number"
+}

addedOutput schema / properties / notice

Added value: +{
+  "description": "Recovery guidance when the filter yields no results or the compound has no bioactivity data.",
+  "type": "string"
+}

addedOutput schema / properties / outcomeFilter

Added value: +{
+  "description": "Outcome filter applied: active, inactive, or all.",
+  "type": "string"
+}

addedOutput schema / properties / returnedCount

Added value: +{
+  "description": "Assays returned after the maxResults cap.",
+  "type": "number"
+}

addedOutput schema / properties / targetFilter

Added value: +{
+  "description": "Target filter applied (gene ID and/or protein accession), when set.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "cid",
-  "totalAssays",
-  "activeCount",
-  "inactiveCount",
-  "results"
-]New value: +[
+  "cid",
+  "totalAssays",
+  "activeCount",
+  "inactiveCount",
+  "results",
+  "outcomeFilter",
+  "filteredCount",
+  "returnedCount"
+]

Changed6 schema fields changedv0.1.22May 31, 2026
- changedInput schema / properties / cid / description
```
Previous value: -"PubChem Compound ID."New value: +"PubChem Compound ID. Resolve from name/SMILES with pubchem_search_compounds."
```
- addedOutput schema / properties / results / items / description
```
Added value: +"Assay result entry."
```
- addedOutput schema / properties / results / items / properties / activityValues / items / description
```
Added value: +"Quantitative activity measurement entry."
```
- changedOutput schema / properties / results / items / properties / activityValues / items / properties / name / description
```
Previous value: -"Measurement name (e.g. IC50, EC50, Ki)."New value: +"Measurement name (e.g. IC50, EC50, Ki). Omitted when not reported."
```
- changedOutput schema / properties / results / items / properties / activityValues / items / properties / unit / description
```
Previous value: -"Unit of measurement (e.g. uM, nM)."New value: +"Unit of measurement (e.g. uM, nM). Omitted when not reported."
```
- changedOutput schema / properties / results / items / properties / activityValues / items / required
```
Previous value: -[
-  "name",
-  "value",
-  "unit"
-]New value: +[
+  "value"
+]
```
First observedv0.1.11Apr 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, and openWorld, so the safety profile is covered. The description adds real behavioral context about the shape of the result (which outcomes, which target identifiers, which quantitative metrics appear), helping the agent interpret output without opening the output schema.

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 sentences, front-loaded with what is returned, followed immediately by the filtering capability and its use case. No filler or restatement of the tool name.

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?

A read-only, paginated query tool with a full output schema and 100% parameter coverage needs only to convey what it returns and how filters shape the result, both of which the description does. Nothing an agent needs to invoke it correctly is missing.

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?

With 100% schema description coverage the baseline is 3, but the description contributes beyond the schema by explaining that outcome and target filters can be combined and what that combination answers. It omits pagination details, but those live in 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?

States a specific verb ('Get') and resource ('a compound's bioactivity profile') and then enumerates exactly what the profile contains: assays, activity outcomes, target identifiers, and quantitative values. This is plainly distinguishable from siblings like get_compound_safety or get_compound_interactions, which would cover different data domains.

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 second sentence tells the agent when and how to narrow the profile ('filter by outcome and/or a specific molecular target') and gives a concrete motivating question ('is this compound active against target T?'). It stops short of naming alternative sibling tools or stating when bioactivity is the wrong choice.

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

Deploy Server