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

Link compounds to protein targets, rank bioactivity, and look up drug mechanisms and indications.

- Trust score: 68/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-20

## Components

- remote · `chembl.caseyjhand.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/cyanheads-chembl-mcp-server/chembl.md), [page](https://verifymcp.io/servers/cyanheads-chembl-mcp-server/chembl)
- npm · `@cyanheads/chembl-mcp-server`: 67/100, [markdown](https://verifymcp.io/servers/cyanheads-chembl-mcp-server/cyanheads-chembl-mcp-server.md), [page](https://verifymcp.io/servers/cyanheads-chembl-mcp-server/cyanheads-chembl-mcp-server)

## Channel facts

- Endpoint: `https://chembl.caseyjhand.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.3`

## 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 2026-08-20.

- **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 7 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**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2870 tokens (~410/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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-chembl-mcp-server https://chembl.caseyjhand.com/mcp
```

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Other

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

### 2026-08-20 (score 68, +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.

### 2026-08-18 (score 67, +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.

### 2026-08-16 (score 66, +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.

### 2026-08-14 (score 65, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-13 (score 64)

First indexed and scored.

## MCP tools (7)

### `chembl_search_molecules` (~470 tokens)

chembl-search-molecules

Discovery entry point for compounds. Find by name / ChEMBL ID / InChIKey with the default search_type=name (supply query), or run a structure search with search_type exact | similarity | substructure (supply structure as a SMILES). At least one of query or structure is required, and structure is required for the three structure modes. Returns ChEMBL ID, preferred name, canonical SMILES, formula, MW, AlogP, Lipinski violations, QED, and max clinical phase on every row; only search_type=similarity adds a Tanimoto similarity percent. Chain molecule_chembl_id into chembl_get_bioactivities or chembl_get_drug_info. A capped result carries nextCursor — pass it back as cursor with the same filters to read the next page.

Input parameters:

- `cursor` (string): Opaque continuation token from a previous call's nextCursor — resumes where that page ended. Omit for the first page. Re-send the same query/structure/filters that minted it (only limit may change; i…
- `limit` (integer): Maximum molecules to return. Defaults to the server default (25) when omitted.
- `max_phase_min` (integer): For search_type=name, restrict to compounds at or above this max clinical phase (e.g. 4 for marketed drugs only).
- `query` (string): Search text for search_type=name — a drug name, ChEMBL ID, or InChIKey, e.g. "imatinib" or "CHEMBL25".
- `search_type` (string): name = text lookup (query); exact = exact structure match; similarity = Tanimoto ≥ threshold; substructure = contains the structure. All structure modes need `structure`.
- `similarity_threshold` (integer): Minimum Tanimoto similarity percent for search_type=similarity (40–100; ChEMBL rejects below 40). Ignored for other modes.
- `structure` (string): SMILES string for structure search, e.g. "CC(=O)Oc1ccccc1C(=O)O". Required when search_type is exact/similarity/substructure.

Output parameters:

- `cap` (number): The limit that was applied.
- `molecules` (array): Matching compounds (up to the limit).
- `nextCursor` (string): Opaque token for the next page — pass it back as cursor with the same filters. Absent when this page is the last one.
- `notice` (string): Guidance when nothing matched — echoes the query and suggests how to broaden.
- `shown` (number): Number of molecules returned.
- `totalCount` (number): Total compounds matching before the limit was applied.
- `truncated` (boolean): True when the result was capped at the limit.

### `chembl_get_bioactivities` (~878 tokens)

chembl-get-bioactivities

The flagship compound↔target bioactivity bridge: measurements for a molecule (target deconvolution / selectivity), a target (lead finding), or both together (how potently one compound hits one target). Supply at least one of molecule_chembl_id (from chembl_search_molecules) or target_chembl_id (from chembl_search_targets) — supplying both narrows to that compound–target pair, supplying neither is an error. Filter by standard_type (IC50/Ki/EC50/…), minimum potency pchembl_value_min, assay_type, and organism. Not every measurement has a derivable pchembl_value, so potency_view picks which side of that split you get: the default "potency_ranked" returns the measurements that have one, most potent first (ChEMBL sorts the rest first otherwise, which is why they are not merged), and "null_potency" returns exactly the measurements that have none. totalCount is the honest full match count across both views either way. Mixing measurement types (IC50 vs Ki) is a scientific error — set standard_type to compare like with like. A popular target carries tens of thousands of rows: results spill to a DataCanvas table (call chembl_dataframe_describe for its columns, then chembl_dataframe_query for honest aggregates across the staged set), while an inline preview answers the immediate question. Each view stages its own table (bioactivities / bioactivities_null_potency), so running both against one canvas_id lets a UNION ALL rebuild the full set. The staged table is capped at CHEMBL_MAX_SPILL_ROWS; when the cap is hit, truncated is true and the table is a bounded slice, not the complete view. The inline rows are always capped at limit, so compare that against totalCount before treating them as the whole answer. Spilling the rest requires CANVAS_PROVIDER_TYPE=duckdb; without it the inline preview is all there is.

Input parameters:

- `assay_type` (string): Restrict to an assay type code: "B" (binding), "F" (functional), "A" (ADMET), "T" (toxicity).
- `canvas_id` (string): Optional canvas ID from a prior call to reuse the same canvas. Each potency_view re-stages its own table, so a second query of the SAME view REPLACES (overwrites) its prior rows — it does not append…
- `limit` (integer): Maximum rows in the inline preview. Defaults to the server default (25). The full set still spills to the canvas.
- `molecule_chembl_id` (string): ChEMBL molecule ID (from chembl_search_molecules), e.g. "CHEMBL941". Supply this, target_chembl_id, or both — both narrows to that compound–target pair.
- `organism` (string): Restrict to a target organism, e.g. "Homo sapiens" (case-insensitive exact match).
- `pchembl_value_min` (number): Minimum pchembl_value (−log10 molar potency), e.g. 7 keeps sub-100 nM activities. Only valid on the potency_ranked view — the null_potency rows have no pchembl_value to compare against.
- `potency_view` (string): Which side of the pchembl_value presence split to retrieve. "potency_ranked" (default) returns the measurements that have a derivable pchembl_value, most potent first. "null_potency" returns exactly…
- `standard_type` (string): Restrict to one measurement type, e.g. "IC50", "Ki", "EC50". Set this to compare potencies validly.
- `target_chembl_id` (string): ChEMBL target ID (from chembl_search_targets), e.g. "CHEMBL203". Supply this, molecule_chembl_id, or both — both narrows to that compound–target pair.

Output parameters:

- `activities` (array): Bioactivity rows for the selected potency_view — the inline preview, or the full view when it fit without spilling.
- `appliedFilters` (object): Filters as the server parsed them.
- `canvasDisabled` (boolean): True when CANVAS_PROVIDER_TYPE is not duckdb, so large sets could not spill — the inline rows are a capped preview, not the full set.
- `canvas_id`: Canvas ID holding the staged table — pass to chembl_dataframe_describe to list its columns, then to chembl_dataframe_query to run SQL over them. Null when canvas is disabled or nothing spilled.
- `notice` (string): Guidance when no measurements matched, or how to SQL the spilled set.
- `potency_view` (string): Which view these rows came from: "potency_ranked" = measurements with a derivable pchembl_value; "null_potency" = measurements with none. Re-call with the other value to reach the rest of totalCount.
- `spilled` (boolean): True when the view exceeded the preview and was staged on the canvas.
- `staged_row_count`: Rows actually registered on the canvas table. Null when nothing spilled. Below the view total when truncated is true.
- `table_name`: Canvas table name holding the staged rowset, and the FROM target for chembl_dataframe_query SQL — "bioactivities" for potency_ranked, "bioactivities_null_potency" for null_potency. Null when not spil…
- `totalCount` (number): Total matching measurements upstream — the honest full count spanning BOTH potency views, before any preview cap. The staged/preview rows are the selected view of this.
- `truncated` (boolean): True when the CHEMBL_MAX_SPILL_ROWS cap was hit before the upstream view was exhausted — the staged table is a bounded slice, NOT the complete view, so aggregates over it are a sample. Narrow the fil…

### `chembl_search_targets` (~388 tokens)

chembl-search-targets

Resolve a protein/gene/UniProt accession to the ChEMBL target ID that chembl_get_bioactivities needs for the target→leads workflow. Supply at least one of accession (UniProt, e.g. P00533), gene_symbol (e.g. EGFR), or query (free-text name); filter further by organism and target_type. Returns each target with its type, organism, and component UniProt accessions + gene symbols. A UniProt accession from the uniprot/protein server is the most precise input. A capped result carries nextCursor — pass it back as cursor with the same filters to read the next page.

Input parameters:

- `accession` (string): UniProt accession of a target component, e.g. "P00533". The most precise resolver — from the uniprot/protein server.
- `cursor` (string): Opaque continuation token from a previous call's nextCursor — resumes where that page ended. Omit for the first page. Re-send the same accession/gene_symbol/query/filters that minted it (only limit m…
- `gene_symbol` (string): Gene symbol of a target component, e.g. "EGFR" (case-insensitive exact match).
- `limit` (integer): Maximum targets to return. Defaults to the server default (25) when omitted.
- `organism` (string): Restrict to a source organism, e.g. "Homo sapiens" (case-insensitive exact match).
- `query` (string): Free-text name match against the target preferred name, e.g. "kinase" or "growth factor receptor".
- `target_type` (string): Restrict to a target class, e.g. "SINGLE PROTEIN" or "PROTEIN COMPLEX".

Output parameters:

- `cap` (number): The limit that was applied.
- `nextCursor` (string): Opaque token for the next page — pass it back as cursor with the same filters. Absent when this page is the last one.
- `notice` (string): Guidance when no target matched — echoes the filters and suggests how to broaden.
- `shown` (number): Number of targets returned.
- `targets` (array): Matching targets (up to the limit).
- `totalCount` (number): Total targets matching the filters before the limit was applied.
- `truncated` (boolean): True when the result was capped at the limit.

### `chembl_get_drug_info` (~237 tokens)

chembl-get-drug-info

Pharmacology for a drug (molecule): mechanism(s) of action, the molecular target(s) it acts on, action type (inhibitor / agonist / …), first-approval year, and clinical indications with the max phase reached for each. Supply molecule_chembl_id (from chembl_search_molecules). Distinct from the openfda server's label/adverse-event view — this is the curated mechanism-and-indication record. A mechanism's target_chembl_id chains into chembl_get_bioactivities for compounds hitting the same target. Each list carries its own retrieval state: an empty mechanisms or indications array means the molecule has none recorded only when the matching mechanisms_status / indications_status is "complete" — "failed" means the upstream request was rejected and the array says nothing about the molecule, and "truncated" means the page cap bounded the list at fewer rows than the matching *_total_count.

Input parameters:

- `molecule_chembl_id` (string, required): ChEMBL molecule ID (from chembl_search_molecules), e.g. "CHEMBL939" for gefitinib.

Output parameters:

- `first_approval`: Year of first approval, e.g. 2003. Null when unapproved or unknown.
- `indications` (array): Clinical indications. Empty is authoritative only when indications_status is "complete".
- `indications_status` (string): Retrieval state of the indication list. "complete" = every row ChEMBL records is present, so an empty array is a fact about the molecule. "truncated" = the single-request page cap bounded the list, s…
- `indications_total_count`: Total indication rows ChEMBL holds for this molecule (upstream page_meta.total_count). Exceeds the returned array length exactly when the status is "truncated". Null when the fetch failed — the count…
- `max_phase`: Max clinical phase across indications: 4 = marketed. Null when unknown.
- `mechanisms` (array): Mechanisms of action. Empty is authoritative only when mechanisms_status is "complete".
- `mechanisms_status` (string): Retrieval state of the mechanism list. "complete" = every row ChEMBL records is present, so an empty array is a fact about the molecule. "truncated" = the single-request page cap bounded the list, so…
- `mechanisms_total_count`: Total mechanism rows ChEMBL holds for this molecule (upstream page_meta.total_count). Exceeds the returned array length exactly when the status is "truncated". Null when the fetch failed — the count…
- `molecule_chembl_id` (string): The ChEMBL molecule ID queried.
- `notice` (string): Disclosure of anything the two lists do not say for themselves: a list whose upstream fetch failed (so its emptiness means nothing), a list the page cap bounded, or — only when both lists came back c…
- `pref_name`: Preferred drug name, e.g. "GEFITINIB". Null when unnamed.

### `chembl_get_assay` (~135 tokens)

chembl-get-assay

Assay provenance behind a bioactivity row: description, type (binding / functional / ADMET / toxicity), the target it measures, organism, and ChEMBL's 1–9 confidence score (9 = direct assay on the protein target, lower = homologous or indirect). Supply assay_chembl_id from a chembl_get_bioactivities row. Call this to judge whether two measurements are comparable before ranking them together.

Input parameters:

- `assay_chembl_id` (string, required): ChEMBL assay ID from a bioactivity row's assay_chembl_id, e.g. "CHEMBL674637".

Output parameters:

- `assay_chembl_id` (string): The ChEMBL assay ID queried.
- `assay_type`: Assay type code: B=binding, F=functional, A=ADMET, T=toxicity, P=physicochemical, U=unclassified. Null when absent.
- `assay_type_description`: Human-readable assay type, e.g. "Binding". Null when absent.
- `confidence_description`: Human-readable confidence description, e.g. "Direct single protein target assigned". Null when absent.
- `confidence_score`: ChEMBL confidence score, 1–9 (9 = direct single-protein assay; lower = homologous/indirect). Null when unscored.
- `description`: Assay description text. Null when absent.
- `organism`: Assay organism. Null when unspecified.
- `target_chembl_id`: ChEMBL target ID the assay measures — chain to chembl_search_targets/chembl_get_bioactivities. Null when unassigned.

### `chembl_dataframe_query` (~296 tokens)

chembl-dataframe-query

Run a read-only SQL SELECT over the bioactivity rows chembl_get_bioactivities spilled to a canvas — rank, group, dedupe, and aggregate across the FULL set, not the inline preview. Reference each staged table by the name chembl_get_bioactivities returned — bioactivities for its potency_ranked view, bioactivities_null_potency for null_potency; discover the staged tables and their columns with chembl_dataframe_describe. Compute honest aggregates here (e.g. SELECT molecule_chembl_id, MEDIAN(pchembl_value) AS med FROM bioactivities WHERE standard_type = 'IC50' GROUP BY 1 ORDER BY 2 DESC). Two independent bounds apply, each reported on its own field: truncated is true when the SQL result exceeded the canvas row cap, and rendered_rows says how many of the returned rows the markdown table holds once its character budget is reached (below row_count on a wide or long result). Page past either bound with SQL LIMIT/OFFSET — append e.g. LIMIT 500 OFFSET 500 and re-call; offsets reach rows beyond the canvas row cap. Requires CANVAS_PROVIDER_TYPE=duckdb.

Input parameters:

- `canvas_id` (string, required): Canvas ID returned by chembl_get_bioactivities (spilled: true).
- `sql` (string, required): A read-only SELECT against the staged tables. Reference tables by the names chembl_get_bioactivities returned.

Output parameters:

- `rendered_rows` (number): How many of those rows the markdown table in content[] holds. Below row_count when the rendered table reached its character budget — a rendering bound, INDEPENDENT of truncated: a response can be tru…
- `row_count` (number): Number of rows materialized in this response.
- `rows` (array): Result rows (capped at the canvas row limit). Each row is a column→value map.
- `truncated` (boolean): True when the SQL result exceeded the canvas row cap and was truncated — the engine bounding the result set itself, not the rendering. Independent of rendered_rows; page past it with LIMIT/OFFSET.

### `chembl_dataframe_describe` (~92 tokens)

chembl-dataframe-describe

List the tables and columns staged on a canvas by chembl_get_bioactivities — inspect before calling chembl_dataframe_query to write correct SQL. Returns each table with its row count, kind (table | view), and column names + types. Requires CANVAS_PROVIDER_TYPE=duckdb.

Input parameters:

- `canvas_id` (string, required): Canvas ID returned by chembl_get_bioactivities (spilled: true).

Output parameters:

- `tables` (array): Tables and views staged on the canvas.

## Diagnostics

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

## Score history

- 2026-08-20: 68
- 2026-08-19: 67
- 2026-08-18: 67
- 2026-08-17: 66
- 2026-08-16: 66
- 2026-08-15: 65
- 2026-08-14: 65
- 2026-08-13: 64

## Links

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