# Agentic Target Evidence (oci · ghcr.io/athril/agentic-target-evidence/mcp-gateway)

Read-only biomedical evidence tools for drug-target validation: DepMap, gnomAD, OpenTargets, PubMed…

- Trust score: 36/100 (low)
- Change this week: +30
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- oci · `ghcr.io/athril/agentic-target-evidence/mcp-gateway`: 36/100 (this document), [markdown](https://verifymcp.io/servers/athril-agentic-target-evidence/ghcr-io-athril-agentic-target-evidence-mcp-gateway.md), [page](https://verifymcp.io/servers/athril-agentic-target-evidence/ghcr-io-athril-agentic-target-evidence-mcp-gateway)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/athril/agentic-target-evidence/mcp-gateway`
- Version: `v0.1.4`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-10-23.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 18 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 2358 tokens (~56/item across 42 items; 42 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 42 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 42 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Agentic Target Evidence MCP server?

Agentic Target Evidence runs locally as a container image, launched with docker run --rm -i -e MCP_TRANSPORT -e NCBI_API_KEY -e USPTO_API_KEY ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add athril-agentic-target-evidence -- docker run --rm -i -e MCP_TRANSPORT -e NCBI_API_KEY -e USPTO_API_KEY ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Cursor

```json
{
  "mcpServers": {
    "athril-agentic-target-evidence": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "NCBI_API_KEY",
        "-e",
        "USPTO_API_KEY",
        "ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4"
      ]
    }
  }
}
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### VS Code

```json
{
  "servers": {
    "athril-agentic-target-evidence": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "NCBI_API_KEY",
        "-e",
        "USPTO_API_KEY",
        "ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4"
      ]
    }
  }
}
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Codex

```bash
codex mcp add athril-agentic-target-evidence -- docker run --rm -i -e MCP_TRANSPORT -e NCBI_API_KEY -e USPTO_API_KEY ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "athril-agentic-target-evidence": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "NCBI_API_KEY",
        "-e",
        "USPTO_API_KEY",
        "ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4"
      ],
      "enabled": true
    }
  }
}
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Hermes

```yaml
mcp_servers:
  athril-agentic-target-evidence:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "MCP_TRANSPORT", "-e", "NCBI_API_KEY", "-e", "USPTO_API_KEY", "ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4"]
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Netclaw

```json
{
  "McpServers": {
    "athril-agentic-target-evidence": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "NCBI_API_KEY",
        "-e",
        "USPTO_API_KEY",
        "ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4"
      ]
    }
  }
}
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Other

```json
{
  "mcpServers": {
    "athril-agentic-target-evidence": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "NCBI_API_KEY",
        "-e",
        "USPTO_API_KEY",
        "ghcr.io/athril/agentic-target-evidence/mcp-gateway:v0.1.4"
      ]
    }
  }
}
```

This image reads MCP_TRANSPORT, NCBI_API_KEY and USPTO_API_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

## 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.

### 2026-10-23 (score 36, +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.

### 2026-10-21 (score 35, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 34, +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.

### 2026-10-17 (score 33, +27)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.00
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-10-14 (score 6, 0)

- [security] Stability: Stability not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to compare.
- [security] Tool safety: Tool safety not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no tool text to scan.
- [functional] Schema quality: Schema quality not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no schema to assess.
- [functional] Capabilities: Protocol version not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we never saw its MCP handshake.
- [functional] Tool coverage: Tool coverage not yet verified: this server's registry entry declares environment variables (an API key or similar), and its server did not start in our sandbox, so we have no tool definitions to assess.

### 2026-10-08 (score 6)

First indexed and scored.

## MCP tools (42)

### `chembl_get_chemistry` (~50 tokens)

Fetch ChEMBL drug-mechanism and bioactivity signals for a ChEMBL target id.

Input parameters:

- `chembl_target_id` (string, required)
- `gene_symbol` (string)

Output parameters:

- `action_types` (array)
- `activity_type_counts` (object)
- `assay_type_counts` (object)
- `chembl_target_id` (string)
- `clinical_candidates` (array)
- `gene_symbol` (string)
- `max_phase`
- `mechanisms_of_action` (array)
- `median_pchembl`
- `num_actives` (integer)
- `num_bioactivities` (integer)
- `num_clinical_candidates` (integer)
- `num_highly_potent` (integer)
- `num_mechanisms` (integer)
- `num_potent` (integer)
- `num_quantitative` (integer)
- `source_link` (string)
- `text` (string)

### `clingen_get_validity` (~31 tokens)

Fetch ClinGen gene-disease validity classifications for a gene.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `associations` (array)
- `gene_symbol` (string)
- `text` (string)
- `total` (integer)

### `clinicaltrials_search_trials` (~64 tokens)

Search ClinicalTrials.gov v2 API for studies involving the gene and disease.

Records without posted results have scope='abstract'; those with results
have scope='full_text'.

Input parameters:

- `disease` (string, required)
- `gene` (string, required)
- `population`

Output parameters:

- `result` (array)

### `clinicaltrials_count_condition_trials` (~76 tokens)

Count trials for a disease/condition regardless of target gene or intervention.

Target-agnostic disease-level trial landscape (contrast with
\`clinicaltrials_search_trials`, which is gene-keyed). Uses count-only queries
so a broad condition search never pages thousands of full study records.

Input parameters:

- `condition` (string, required)

Output parameters:

- `active_count` (integer)
- `condition` (string)
- `mapping` (string)
- `phase3_count` (integer)
- `recruiting_count` (integer)
- `source_link` (string)
- `text` (string)
- `total_count` (integer)

### `depmap_get_dependency` (~33 tokens)

Fetch DepMap CRISPR gene effect and dependency scores for a gene.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `dependency_fraction`
- `gene_effect_mean`
- `gene_effect_median`
- `gene_effect_q1`
- `gene_effect_q3`
- `gene_effect_std`
- `gene_symbol` (string)
- `is_common_essential` (boolean)
- `is_strongly_selective` (boolean)
- `lineage_breakdown` (array)
- `num_dependent_lines`
- `selective_lineages` (array)
- `source_link` (string)
- `text` (string)
- `total_lines`

### `dgidb_get_gene_drug_interactions` (~116 tokens)

Fetch curated drug-gene interaction claims for a gene from DGIdb.

Returns drugs known to interact with the gene's product, ranked by DGIdb's
normalized interaction score, with mechanism (interaction type/directionality,
e.g. inhibitor/INHIBITORY), supporting PMIDs, and contributing source databases.
Set approved_only=True to restrict to drugs with regulatory approval.

Input parameters:

- `approved_only` (boolean)
- `gene_symbol` (string, required)
- `max_results` (integer)

Output parameters:

- `gene_concept_id` (string)
- `gene_symbol` (string)
- `interactions` (array)
- `text` (string)
- `total_count` (integer)

### `dgidb_get_gene_categories` (~84 tokens)

Fetch DGIdb gene-category annotations for a gene.

Returns category labels (e.g. DRUGGABLE GENOME, KINASE, CLINICALLY ACTIONABLE,
DRUG RESISTANCE) each with the source databases asserting it, plus a convenience
\`is_druggable_genome` flag.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `categories` (array)
- `gene_symbol` (string)
- `is_druggable_genome` (boolean)
- `text` (string)

### `encode_get_regulatory_coverage` (~53 tokens)

Fetch regulatory-assay (ChIP-seq/DNase-seq/ATAC-seq) coverage at a gene locus.

Input parameters:

- `gene_symbol` (string, required)
- `genome` (string)

Output parameters:

- `coordinates` (string)
- `gene_symbol` (string)
- `source_link` (string)
- `text` (string)
- `top_assays` (array)
- `top_organs` (array)
- `top_targets` (array)
- `total_experiments` (integer)

### `expression_atlas_get_differential_expression` (~59 tokens)

Fetch disease-vs-control differential expression for a gene from Expression Atlas.

Input parameters:

- `disease` (string)
- `ensembl_id` (string)
- `gene_symbol` (string, required)
- `species` (string)

Output parameters:

- `disease` (string)
- `disease_specific` (boolean)
- `ensembl_id` (string)
- `gene_symbol` (string)
- `results` (array)
- `source_link` (string)
- `text` (string)

### `gencc_get_validity` (~35 tokens)

Fetch GenCC's per-submitter gene-disease validity classifications for a gene.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `associations` (array)
- `gene_symbol` (string)
- `hgnc_id`
- `text` (string)
- `total` (integer)

### `gnomad_get_constraint` (~52 tokens)

Fetch gnomAD gene-level LoF/missense/synonymous constraint (LOEUF, pLI, pRec, MOEUF, syn_z).

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `ensembl_id` (string)
- `exp_lof`
- `exp_mis`
- `exp_syn`
- `gene_symbol` (string)
- `loeuf`
- `mis_z`
- `moeuf`
- `obs_lof`
- `obs_mis`
- `obs_syn`
- `oe_lof`
- `oe_lof_lower`
- `oe_mis`
- `oe_mis_lower`
- `pli`
- `source_link` (string)
- `syn_z`
- `text` (string)

### `gnomad_get_clinvar_variants` (~47 tokens)

Fetch ClinVar variants overlapping this gene from gnomAD's integrated dataset.

Input parameters:

- `ensembl_id` (string, required)
- `gene_symbol` (string)

Output parameters:

- `benign` (array)
- `ensembl_id` (string)
- `gene_symbol` (string)
- `likely_pathogenic` (array)
- `pathogenic` (array)
- `text` (string)
- `total_clinvar` (integer)

### `gnomad_get_lof_variants` (~51 tokens)

Fetch observed high-confidence pLoF variants (natural knockouts) from gnomAD v4.

Input parameters:

- `ensembl_id` (string, required)
- `gene_symbol` (string)

Output parameters:

- `ancestry_skewed` (boolean)
- `any_homozygous` (boolean)
- `ensembl_id` (string)
- `gene_symbol` (string)
- `hc_lof_count` (integer)
- `max_af`
- `reported_variants` (array)
- `text` (string)

### `gtex_get_expression` (~42 tokens)

Fetch GTEx median tissue TPM and HPA protein localization for a gene.

Input parameters:

- `ensembl_id` (string)
- `gene_symbol` (string, required)

Output parameters:

- `ensembl_id` (string)
- `gene_symbol` (string)
- `gtex_expressions` (array)
- `hpa_rna_tissue_category` (string)
- `hpa_subcellular_location` (array)
- `hpa_tissue_specificity` (string)
- `source_link` (string)
- `text` (string)
- `uniprot_accession` (string)

### `gwas_catalog_get_associations` (~54 tokens)

Fetch genome-wide significant GWAS associations for a gene from EBI GWAS Catalog.

Input parameters:

- `gene_symbol` (string, required)
- `max_associations` (integer)
- `p_threshold` (number)

Output parameters:

- `all_traits` (array)
- `dropped_off_target` (integer)
- `gene_symbol` (string)
- `hits` (array)
- `kept_traits` (array)
- `source_link` (string)
- `text` (string)

### `impc_get_phenotypes` (~34 tokens)

Fetch IMPC statistically significant knockout-mouse phenotype calls for a gene.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `gene_symbol` (string)
- `phenotypes` (array)
- `source_link` (string)
- `text` (string)
- `total` (integer)
- `viability` (string)

### `hgnc_resolve_symbol` (~37 tokens)

Resolve a gene symbol (including aliases/previous symbols) to its canonical HGNC record.

Input parameters:

- `symbol` (string, required)

Output parameters:

- `aliases` (array)
- `ensembl_gene_id` (string)
- `hgnc_id` (string)
- `previous_symbols` (array)
- `symbol` (string)

### `mondo_resolve_term` (~37 tokens)

Resolve a disease name or existing ontology id to its MONDO term and cross-references.

Input parameters:

- `name_or_id` (string, required)

Output parameters:

- `label` (string)
- `mondo_id` (string)
- `xrefs` (object)

### `hpo_get_phenotypes` (~36 tokens)

Fetch HPO phenotype breadth/specificity and inheritance-mode hints for a gene.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `gene_symbol` (string)
- `hgnc_id`
- `inheritance_modes` (array)
- `phenotype_count` (integer)
- `specificity_band` (string)
- `text` (string)
- `top_phenotypes` (array)

### `openalex_resolve_journal` (~53 tokens)

Resolve a journal's OpenAlex quality signal from ISSN (preferred) or title.

Input parameters:

- `essn` (string)
- `issn` (string)
- `journal_title` (string)

Output parameters:

- `display_name`
- `established`
- `h_index`
- `is_in_doaj`
- `issn_l`
- `match_type`
- `matched` (boolean)
- `quality_score`
- `source_id`
- `two_yr_mean_citedness`
- `works_count`

### `openfda_search_drug_labels` (~67 tokens)

Search FDA drug labels for drugs mentioning the gene in mechanism of action
or approved for the given indication.

Returns up to 20 deduplicated label records (NON_SENSITIVE, public API).

Input parameters:

- `gene_symbol` (string, required)
- `indication` (string, required)

Output parameters:

- `result` (array)

### `openfda_search_adverse_events` (~79 tokens)

Fetch FAERS adverse event summary for a drug name.

Returns total, serious, and death report counts plus the top 25 reactions
by frequency. FAERS has significant noise — treat as signal-generating, not
ground truth (underreporting, confounders, duplicate submissions).

Input parameters:

- `drug_name` (string, required)

Output parameters:

- `death_rate`
- `death_reports` (integer)
- `drug_name` (string)
- `serious_rate`
- `serious_reports` (integer)
- `source_link` (string)
- `text` (string)
- `top_reactions` (array)
- `total_reports` (integer)

### `openfda_count_indication_drugs` (~98 tokens)

Count FDA-approved drugs for an indication, regardless of target gene.

Target-agnostic disease-level competitive landscape (contrast with
\`openfda_search_drug_labels`, which is gene-keyed). Returns the approved-drug
count, drug names, a few mechanism-of-action examples, and which query path
matched (`phrase` / `broad` / `none`).

Input parameters:

- `indication` (string, required)

Output parameters:

- `approved_drug_count` (integer)
- `drugs` (array)
- `indication` (string)
- `mapping` (string)
- `moa_examples` (array)
- `source_link` (string)
- `text` (string)

### `opentargets_get_associations` (~86 tokens)

Fetch gene-disease association scores from the Open Targets Platform.

gene_id must be an Ensembl ID (e.g. ENSG00000012048 for BRCA1).
disease_id must be an EFO ID (e.g. EFO_0000305 for breast carcinoma).

Input parameters:

- `disease_id` (string, required)
- `gene_id` (string, required)

Output parameters:

- `animal_model_score` (number)
- `disease_id` (string)
- `gene_id` (string)
- `genetic_score` (number)
- `known_drugs_score` (number)
- `literature_score` (number)
- `overall_score` (number)
- `rna_expression_score` (number)
- `somatic_mutations_score` (number)
- `source_link` (string)
- `text` (string)

### `opentargets_get_tractability` (~60 tokens)

Fetch tractability evidence for a gene from the Open Targets Platform.

Returns small-molecule and antibody tractability flags plus any other
modalities (PROTAC, oligonucleotide, etc.).

Input parameters:

- `gene_id` (string, required)

Output parameters:

- `antibody` (boolean)
- `gene_id` (string)
- `other_modalities` (array)
- `small_molecule` (boolean)
- `source_link` (string)
- `text` (string)

### `opentargets_resolve_gene` (~41 tokens)

Resolve a gene symbol (e.g. BRCA1) to its Ensembl ID via Open Targets search.

Input parameters:

- `symbol` (string, required)

Output parameters:

- `result` (string)

### `opentargets_resolve_disease` (~46 tokens)

Resolve a disease name (e.g. 'breast cancer') to its EFO/MONDO ID via Open Targets search.

Input parameters:

- `name` (string, required)

Output parameters:

- `result` (string)

### `opentargets_get_l2g_scores` (~106 tokens)

Fetch GWAS Locus-to-Gene (L2G) evidence for a gene-disease pair (OT Genetics).

Returns GWAS credible sets where this gene is prioritized as the likely causal gene
for the given disease. gene_id must be an Ensembl ID; disease_id must be an
EFO/MONDO ontology ID.

Input parameters:

- `disease_id` (string, required)
- `gene_id` (string, required)
- `max_results` (integer)

Output parameters:

- `disease_id` (string)
- `gene_id` (string)
- `hits` (array)
- `text` (string)

### `opentargets_get_colocalizations` (~95 tokens)

Fetch eQTL/pQTL ↔ GWAS colocalisations for a gene (OT Genetics).

Returns molecular QTL signals for this gene that colocalize with GWAS loci
(posterior H4 >= h4_threshold). gene_id must be an Ensembl ID.

Input parameters:

- `gene_id` (string, required)
- `h4_threshold` (number)
- `max_results` (integer)

Output parameters:

- `all_traits` (array)
- `dropped_off_target` (integer)
- `gene_id` (string)
- `hits` (array)
- `kept_traits` (array)
- `text` (string)

### `opentargets_get_known_drugs` (~76 tokens)

Fetch known drugs targeting a gene from the Open Targets Platform.

Returns drug name, type, clinical phase, approval status, mechanism of action,
and the indication each drug is being developed for.
gene_id must be an Ensembl ID.

Input parameters:

- `gene_id` (string, required)
- `max_results` (integer)

Output parameters:

- `drugs` (array)
- `gene_id` (string)
- `text` (string)
- `total_count` (integer)

### `opentargets_get_safety` (~75 tokens)

Fetch safety liabilities for a gene from the Open Targets Platform.

Returns curated adverse event and toxicity signals (hepatotoxicity, cardiotoxicity,
nephrotoxicity, etc.) from FDA FAERS and toxicology databases.
gene_id must be an Ensembl ID.

Input parameters:

- `gene_id` (string, required)

Output parameters:

- `gene_id` (string)
- `liabilities` (array)
- `text` (string)

### `opentargets_get_mouse_phenotypes` (~73 tokens)

Fetch mouse knock-out phenotypes for a gene from Open Targets (MGI/IMPC).

Returns phenotypic consequences of disrupting the mouse orthologue, establishing
biological plausibility and early safety signals.
gene_id must be an Ensembl ID.

Input parameters:

- `gene_id` (string, required)

Output parameters:

- `gene_id` (string)
- `phenotypes` (array)
- `text` (string)

### `orphanet_get_associations` (~34 tokens)

Fetch Orphanet rare-disease gene-disease associations for a gene.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `associations` (array)
- `gene_symbol` (string)
- `text` (string)
- `total` (integer)

### `orphanet_get_prevalence` (~39 tokens)

Fetch Orphanet disease-prevalence records for a set of OrphaCodes.

Input parameters:

- `orphacodes` (array, required)

Output parameters:

- `orphacodes` (array)
- `records` (array)
- `text` (string)
- `total` (integer)

### `project_score_get` (~35 tokens)

Fetch Project Score (Sanger) CRISPR fitness/dependency data for a gene.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `bf_scaled_mean`
- `bf_scaled_median`
- `bf_scaled_std`
- `cancer_specific_core_fitness_tissues` (array)
- `fitness_fraction`
- `gene_symbol` (string)
- `is_pancan_core_fitness` (boolean)
- `num_fitness_lines`
- `sidg_id` (string)
- `source_link` (string)
- `text` (string)
- `total_lines`

### `pubmed_search` (~72 tokens)

Search PubMed using the NCBI E-utilities API.

Respects the NCBI free-tier rate limit (3 req/s).  Pass an
NCBI_API_KEY env var to raise the limit to 10 req/s.

Input parameters:

- `max_results` (integer)
- `query` (string, required)

Output parameters:

- `result` (array)

### `pubmed_fetch_abstract` (~31 tokens)

Fetch the abstract and metadata for a single PubMed article.

Input parameters:

- `pmid` (string, required)

Output parameters:

- `abstract` (string)
- `authors` (array)
- `pmid` (string)
- `pub_year`
- `title` (string)

### `pubmed_fetch_pmc_record` (~40 tokens)

Return full-text availability info via PubMed Central.

Returns None if the article is not in PMC.

Input parameters:

- `pmid` (string, required)

Output parameters:

- `result`

### `spoke_get_gene_disease_associations` (~37 tokens)

Fetch SPOKE Disease-ASSOCIATES-Gene edges for a gene symbol.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `associations` (array)
- `gene_symbol` (string)
- `source_link` (string)
- `text` (string)

### `spoke_get_anatomy_expression` (~33 tokens)

Fetch SPOKE Anatomy-Gene expression edges for a gene symbol.

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `expressions` (array)
- `gene_symbol` (string)
- `source_link` (string)
- `text` (string)

### `uniprot_get_protein_profile` (~40 tokens)

Fetch the reviewed human UniProt protein profile (class, location, ChEMBL xref).

Input parameters:

- `gene_symbol` (string, required)

Output parameters:

- `chembl_target_id` (string)
- `function` (string)
- `gene_symbol` (string)
- `protein_classes` (array)
- `protein_name` (string)
- `source_link` (string)
- `subcellular_location` (array)
- `text` (string)
- `uniprot_accession` (string)

### `uspto_search_patents` (~51 tokens)

Search PatentsView for patents referencing the gene and disease.

All results are classified NON_SENSITIVE (patent data is public).

Input parameters:

- `disease` (string, required)
- `gene` (string, required)

Output parameters:

- `result` (array)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/athril-agentic-target-evidence/ghcr-io-athril-agentic-target-evidence-mcp-gateway#diagnostics

## Score history

- 2026-10-23: 36
- 2026-10-22: 35
- 2026-10-21: 35
- 2026-10-20: 34
- 2026-10-19: 34
- 2026-10-18: 33
- 2026-10-17: 33
- 2026-10-16: 6
- 2026-10-15: 6
- 2026-10-14: 6
- 2026-10-13: 6
- 2026-10-12: 6
- 2026-10-10: 6
- 2026-10-08: 6

## Common questions

### What is the Agentic Target Evidence MCP server?

Agentic Target Evidence is an MCP server listed in the public MCP registry as io.github.athril/agentic-target-evidence. Read-only biomedical evidence tools for drug-target validation: DepMap, gnomAD, OpenTargets, PubMed… This page covers its container image (ghcr.io/athril/agentic-target-evidence/mcp-gateway).

### Is the Agentic Target Evidence MCP server safe to use?

Agentic Target Evidence scores 36 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agentic Target Evidence MCP server expose?

Agentic Target Evidence exposes 42 tools: chembl_get_chemistry, clingen_get_validity, clinicaltrials_search_trials, clinicaltrials_count_condition_trials, depmap_get_dependency, and 37 more. Their descriptions and schemas cost roughly 2,358 tokens of context every time the server is loaded.

### Is the Agentic Target Evidence MCP server still maintained?

Agentic Target Evidence is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- GitHub Container Registry: https://ghcr.io/athril/agentic-target-evidence/mcp-gateway
- Repository: https://github.com/athril/agentic-target-evidence
- Changelog RSS feed: https://verifymcp.io/servers/athril-agentic-target-evidence/ghcr-io-athril-agentic-target-evidence-mcp-gateway.xml
- Changelog JSON feed: https://verifymcp.io/servers/athril-agentic-target-evidence/ghcr-io-athril-agentic-target-evidence-mcp-gateway.json
- HTML version of this page: https://verifymcp.io/servers/athril-agentic-target-evidence/ghcr-io-athril-agentic-target-evidence-mcp-gateway