MCP server for ITASCA PFC, FLAC3D, 3DEC, MPoint and MassFlow: search docs, run simulations, plot.
TS Second Opinion is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Second opinion on ML transition-state guesses: trust, check with DFT or re-generate
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ts-second-opinion-mcp '--' uvx ts-second-opinion
# 2 — ask your agent for something these tools do
# list_reactions, triage_reaction, triage_structures and 10 more
TS Second Opinion costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts TS Second Opinion as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user ts-second-opinion-mcp '--' uvx ts-second-opinionReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
13 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List reactions in the RDB7 test set (1,194 reactions, 8 GoFlow guesses each) with their triage verdict.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| verdict | string | no | — |
| mirror_repaired | boolean | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
Triage one RDB7 test reaction: run every gated rule on all 8 GoFlow guesses, pick the consensus among guesses that pass, repair a wrong-handed stereocentre by mirroring if that makes it pass, and return a verdict with reasons and the recommended TS geometry (xyz). score_against_reference adds…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reaction_id | integer | yes | — |
| score_against_reference | boolean | no | — |
Triage your own reaction, from any TS generator and with any elements. Give the reactant and product geometries and one or more TS guesses as xyz text (multi-frame xyz allowed); several guesses enable the model-disagreement signal. mapped_reaction_smiles is optional: without it, bonds, bond orders…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reactant_xyz | string | yes | — |
| product_xyz | string | yes | — |
| guesses_xyz | array | yes | — |
| mapped_reaction_smiles | string | no | — |
| order | string | no | — |
| charge | integer | no | — |
| multiplicity | integer | no | — |
Triage many reactions on disk at once. path: a folder with one sub-folder per reaction (reactant.xyz, product.xyz, the TS guess .xyz files, optional reaction.smi), or a .csv with columns id, reactant, product, guesses (and optional smiles, charge, multiplicity). Writes out_dir/verdicts.csv, the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | — |
| out_dir | string | no | — |
| charge | integer | no | — |
| multiplicity | integer | no | — |
| reports | boolean | no | — |
List the plain-English rules, their gate results, and whether each is used in triage.
Takes no parameters.
Show the Python code of a rule, so you can read it or use it as an example.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
Test a candidate rule check against 9,540 real DFT transition states (RDB7 training set) and distorted ones.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rule_text | string | yes | — |
| python_source | string | yes | — |
Save a rule check that passes the gate (re-tested on save). By default it goes to tsso/checks_user and is not used in triage; set use_in_triage=True only when a person has asked for it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| rule_text | string | yes | — |
| python_source | string | yes | — |
| use_in_triage | boolean | no | — |
Write an ORCA TS-optimisation input (wB97X-D4/def2-TZVP OptTS Freq, as in GoFlow's tsopt.inp) for the recommended guess of a test reaction. Returns the file paths and input text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reaction_id | integer | yes | — |
Data-quality audit of RDB7: reactions whose reactant or product geometry contradicts the atom-mapped SMILES (atoms at single-bond distance that the SMILES does not bond, or a SMILES bond whose atoms are far apart).
Takes no parameters.
Stereo-aware evaluation of any TS generator: multi-frame xyz text of predictions and of reference TSs (one frame per reaction, same order) plus the atom-mapped reaction SMILES. Returns D-MAE, RMSD with and without the mirror image allowed, success rate, share with correct handedness, and success…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| predictions_xyz | string | yes | — |
| references_xyz | string | yes | — |
| reaction_smiles | array | yes | — |
| order | string | no | — |
Certified trust (conformal selection): calibrate on a random half of the RDB7 test reactions, then return which of the other half can be trusted so that, on average, at most target_error_rate of the trusted ones are wrong. count: 'geometry' (D-MAE > 0.2 A; what matters for barriers) or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target_error_rate | number | no | — |
| count | string | no | — |
| seed | integer | no | — |
Headline results, split into geometry errors and handedness errors: rates before and after, how many wrong-handed guesses the rules catch and how many are whole mirror images (same energy, so even DFT would not flag them), certified-trust numbers, and risk-coverage curves.
Takes no parameters.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install TS Second Opinion or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (13 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_reactions | no tags | |
| triage_reaction | no tags | |
| triage_structures | no tags | |
| triage_batch | no tags | |
| list_rules | no tags | |
| get_rule_source | no tags | |
| gate_check | no tags | |
| save_rule | no tags | |
| write_orca_input | no tags | |
| audit_rdb7_dataset | no tags | |
| evaluate_predictions | no tags | |
| certify_trust | no tags | |
| benchmark_summary | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish TS Second Opinion can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.