Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PDBeurope/PDBe-MCP-Servers --skill molview-specgit clone --depth 1 https://github.com/PDBeurope/PDBe-MCP-ServersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pdbeurope/pdbe-mcp-servers/molview-spec)<a href="https://agentmods.dev/skills/pdbeurope/pdbe-mcp-servers/molview-spec"><img src="https://agentmods.dev/badge/skills/pdbeurope/pdbe-mcp-servers/molview-spec/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pdbeurope/pdbe-mcp-servers/molview-spec"><img src="https://agentmods.dev/badge/skills/pdbeurope/pdbe-mcp-servers/molview-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.01286 |
| Opus 5.5 | $0.00022 | $0.00514 |
| Sonnet 5.5 | $0.00011 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
molview-spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Molecular views and stories
Use the advertised ebi-pdbe-build_mvs tool for custom single scenes and
ebi-pdbe-build_mvs_story for a guided story. Use their advertised legacy aliases
only on servers that expose those names. Ordinary structure exploration uses
ebi-pdbe-open_structure; aligned comparison uses ebi-pdbe-compare_structures.
For any initial request to open, view, inspect, or show a structure or PDB entry—including
a request that only supplies an entry ID—call ebi-pdbe-open_structure. Never call
ebi-pdbe-load_structure_annotations for a user request: it is an App-only helper for
loading optional annotations into a workspace that is already open and does not create a scene.
A successful explorer result (status: "prepared") completes that viewing
request. Stop calling visualization tools; do not repeatedly reopen the entry
or switch to another viewer tool to wait for browser rendering.
The App displays supplied scientific data. Preserve PDBe/SIFTS residue correspondence and supplied alignment transforms. Do not calculate RMSD, per-residue displacement, distance-cutoff ligand neighbourhoods or inferred binding sites. Highlight binding-site residues only from explicit source annotations with provenance; if absent, report the annotation as unavailable. Coordinate loading and camera navigation do not establish new scientific results.
Ground biological claims, residue mappings, ligand instances and scene choices in PDBe evidence. Read scene guidance when building or modifying a scene, and story guidance for a tour or story. The tool schemas are authoritative; full schema resources are available at scene schema and story schema when exact field details are needed. Read the builder API reference for transforms, instances, additional structures, primitives, annotation tables and serialized MolQL. The same operations work inside each story scene.
On servers advertising ebi-pdbe-update_workspace, recover the latest complete
workspace for the exact target viewer from App context or structured tool output.
For follow-up changes, call that tool with the workspace, its revision as
expected_revision, and a suitable operation batch. Preserve unrelated layers,
structures, source annotations and transforms. Upserts replace complete named
definitions. Use only component/annotation layers with explicit data selections;
calculated binding_site layers and cutoff fields are unsupported. Use the
source PDBe/SIFTS residue correspondence table and export without adding geometric
measurements. A shared resource URI alone does not route results to an existing
viewer: the host must match the target workspace ID.
On older servers without workspace updates, recover the complete builder and
use the established full-replacement builder workflow. Do not pass host routing
fields such as pdbe_visualization_request.mode to PDBe tools. If the requested
viewer state is unavailable, recover it before constructing the edit.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 102 lines · 54 tokens per session scan A e61b619fc482
molview-spec is a skill published in the GitHub repository PDBeurope/PDBe-MCP-Servers (44 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,286 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.
molview-spec compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| molview-specPDBeurope/PDBe-MCP-Servers | Skill | 44 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| sc-cell-annotationTianGzlab/OmicsClaw | Skill | 161 | 1mo ago | Apache-2.0 | A | 73 | Claude Code, Codex |
| sc-ambient-removalTianGzlab/OmicsClaw | Skill | 161 | 1mo ago | Apache-2.0 | A | 59 | Claude Code, Codex |
| sc-cell-communicationTianGzlab/OmicsClaw | Skill | 161 | 1mo ago | Apache-2.0 | A | 69 | Claude Code, Codex |
| sc-clusteringTianGzlab/OmicsClaw | Skill | 161 | 1mo ago | Apache-2.0 | A | 73 | Claude Code, Codex |
| sc-deTianGzlab/OmicsClaw | Skill | 161 | 1mo ago | Apache-2.0 | A | 51 | Claude Code, Codex |
| sc-enrichmentTianGzlab/OmicsClaw | Skill | 161 | 1mo ago | Apache-2.0 | A | 71 | Claude Code, Codex |