Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ScienceLogo

OCI · GHCR.IO/SCIENCELOGO/SCIENCELOGO-MCP

Write and validate ScienceLogo workflows from any AI agent.

+3 this week 39 Trust /100

Last scanned (16 hours ago)

Scores higher than 35% of OCI servers

Category Developer Tools

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security0
  • 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.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency32
Schema Quality & AI Usability71
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 1983 tokens (~79/item across 25 items; 24 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "remove_item" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 26 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

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.

What we tested

Checks we ran (12)

  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (4)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain Security (scores 0 for this)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 in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  • Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
  • Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +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.

  • 14 Nov 26 +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.

  • 12 Nov 26 +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.

  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 33

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed oci/ghcr.io/sciencelogo/sciencelogo-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 24 exposed · ~1,926 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
add_include ~51

Include an existing file (relative to the main file), after the item `after` or after the last include.

NameTypeReqDescription
after–––
entrystringyes–
pathstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

add_mapping ~51

State that a record (`target`) implements a record interface.

NameTypeReqDescription
after–––
entrystringyes–
file–––
implementsstringyes–
targetstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

add_paired_stage ~166

Add or replace a paired stage, which states what is known when it starts and ends. `entry_state` has information, environment and factors (records as JSON). Each call has `procedure`, optional `performer`, `inputs` (input name to location, such as "information.elapsed") and `into` (a location). The exit state is derived from the entry state plus every `into` location unless `exit_state` is given.

NameTypeReqDescription
about–––
after–––
before–––
calls–––
commands–––
entrystringyes–
entry_stateobjectyes–
exit_state–––
file–––
namestringyes–
performer–––

Structured output declared, but exposes no named fields.

No examples provided.

add_phase ~67

Add or replace a phase: a named group of workflow-level stages or other phases, in method order, with its own summary.

NameTypeReqDescription
about–––
entrystringyes–
file–––
membersarrayyes–
namestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

add_requirement ~63

Require that the method calls a procedure (`call`, one target) or runs stages in order (`stage_order`, two or more stages).

NameTypeReqDescription
entrystringyes–
file–––
kindstringyes–
targetsarrayyes–

Structured output declared, but exposes no named fields.

No examples provided.

add_stage ~93

Add or replace a simple stage: a named section of the method with its commands (ScienceLogo text). A new stage gets its own file under stages/ unless `file`, `after` or `before` place it.

NameTypeReqDescription
about–––
after–––
before–––
commands–––
entrystringyes–
file–––
namestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

check ~76

Check a workflow or library with the ScienceLogo reader, without running it. `entry` is the main file; the files it includes are read too. Returns status "valid" with the structural assessment and readability advice, or status "invalid" with the reader's message, file, line and column.

NameTypeReqDescription
entrystringyes–

Structured output declared, but exposes no named fields.

No examples provided.

convert_syntax ~58

Rewrite the files of a workflow or library in verbose or compact syntax with the reference translator, keeping comments. With `file`, only that file.

NameTypeReqDescription
entrystringyes–
file–––
tostringyes–

Structured output declared, but exposes no named fields.

No examples provided.

create_library ~73

Start a library project in a new main file (usually library.rkt). A library holds procedures, record interfaces, includes and imports. `language` is the language version it is written for (default: the installed release).

NameTypeReqDescription
filestringyes–
language–––
namestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

create_workflow ~44

Start a new workflow in a new main file, with its title and summary.

NameTypeReqDescription
about–––
filestringyes–
titlestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

declare_interface ~118

Declare a record interface: the fields a record must or may have. Each field has a `name` and optionally `type` (number, text, boolean, list, record or an interface), `default`, `unit` and `required` (default true). `body` is optional ScienceLogo text for conditions and other interface entries.

NameTypeReqDescription
body–––
entrystringyes–
extends–––
fieldsarrayyes–
file–––
namestringyes–
version–––

Structured output declared, but exposes no named fields.

No examples provided.

declare_performer ~81

Declare who or what carries out work, for example fields {"kind": "human", "role": "scientist"}. Values are JSON; null is unknown; {"expr": "..."} is a ScienceLogo expression.

NameTypeReqDescription
entrystringyes–
fieldsobjectyes–
file–––
namestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

declare_procedure ~179

Declare a procedure. For a step done outside ScienceLogo, describe it as a method, never by file paths or code: `about` says what it does, `inputs` what goes in, `result` the fields of what comes out (each with name, type and unit), and `uncertainty` where the result's uncertainty comes from (each with name and description, or omitted: true). The server writes the result's record interface and an output of that record. `body` is ScienceLogo commands, when the work is written in ScienceLogo itself.

NameTypeReqDescription
aboutstringyes–
body–––
entrystringyes–
file–––
inputsarrayyes–
namestringyes–
result–––
uncertainty–––

Structured output declared, but exposes no named fields.

No examples provided.

declare_proposition ~86

Declare a hypothesis, assumption or conclusion. `children` is optional ScienceLogo text for nested propositions, such as `hypotheses = [h1 = [text = "..."]]`.

NameTypeReqDescription
children–––
entrystringyes–
file–––
namestringyes–
statementstringyes–
typestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

declare_resource ~62

Declare a resource the method uses, such as an instrument or a data source, with its fields (values as in declare_performer).

NameTypeReqDescription
entrystringyes–
fieldsobjectyes–
file–––
namestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

describe_library ~78

What a library provides, before importing it: its name, the language version it is written for, and its procedures (inputs and summary) and record interfaces (fields). The reader fetches it with Git, pinned to `version` (a tag or commit).

NameTypeReqDescription
urlstringyes–
versionstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

import_library ~75

Import a library pinned to a Git tag or commit, under an alias. The reader fetches it with Git when it checks the workflow. `describe_library` shows what a library provides.

NameTypeReqDescription
aliasstringyes–
entrystringyes–
urlstringyes–
versionstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

language_reference ~72

The ScienceLogo documentation of the installed release. With no topic, the list of topics and examples. A topic is a manual page (such as "stages" or "procedures"), "grammar-ebnf", "changelog", or "example:<name>" for an example file.

NameTypeReqDescription
topic–––

Structured output declared, but exposes no named fields.

No examples provided.

move_item ~65

Move an item (`kind:name`) with its comments to another file. A new file is created and included where the item was, so the method keeps its order.

NameTypeReqDescription
entrystringyes–
itemstringyes–
to_filestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

outline ~51

The structure of a valid workflow or library: its title and summary, every item with its kind, name and file, and its stages, phases, procedures, performers and imports.

NameTypeReqDescription
entrystringyes–

Structured output declared, but exposes no named fields.

No examples provided.

read_workflow ~90

The text of a workflow or library, in verbose (default) or compact syntax. With `item` (`kind:name`), only that item. A workflow the current reader rejects is returned as stored, with the reader's error, so it can be rewritten in the current release.

NameTypeReqDescription
entrystringyes–
item–––
syntax_formstring––

Structured output declared, but exposes no named fields.

No examples provided.

remove_item ~36

Remove an item (`kind:name`) with the comments just before it.

NameTypeReqDescription
entrystringyes–
itemstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

set_workflow ~45

Set the workflow's title and its summary (about); either can be left as it is.

NameTypeReqDescription
about–––
entrystringyes–
title–––

Structured output declared, but exposes no named fields.

No examples provided.

write_fragment ~146

Write any ScienceLogo text, checked by the reader before it is saved. By default the text goes at the end of `file` (relative to the main file; default the main file itself). `after`, `before` or `replaces` place it next to or in place of an item (`kind:name`). A new `file` gets its header and an `include` line in the main file, after `include_after` or after the last include.

NameTypeReqDescription
after–––
before–––
entrystringyes–
file–––
include_after–––
replaces–––
textstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the ScienceLogo MCP server?

ScienceLogo runs locally as a container image, launched with docker run --rm -i ghcr.io/sciencelogo/sciencelogo-mcp:0.2.0, plus the required --mount and --workdir, which you supply. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/sciencelogo/sciencelogo-mcp

# add to Claude Code
claude mcp add sciencelogo-sciencelogo-mcp -- docker run --rm -i ghcr.io/sciencelogo/sciencelogo-mcp:0.2.0

Incomplete: the registry marks --mount and --workdir as required and gives no value we can show, so they are not in this command. Add them before you run it.

Common questions

What is the ScienceLogo MCP server?

ScienceLogo is an MCP server listed in the public MCP registry as io.github.ScienceLogo/sciencelogo-mcp. Write and validate ScienceLogo workflows from any AI agent. This page covers its container image (ghcr.io/sciencelogo/sciencelogo-mcp).

Is the ScienceLogo MCP server safe to use?

ScienceLogo scores 39 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 ScienceLogo MCP server expose?

ScienceLogo exposes 24 tools: check, outline, read_workflow, language_reference, create_workflow, and 19 more. Their descriptions and schemas cost roughly 1,926 tokens of context every time the server is loaded.

Is the ScienceLogo MCP server still maintained?

ScienceLogo is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the ScienceLogo MCP server?

VerifyMCP ran 12 checks on ScienceLogo, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about ScienceLogo: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.