Ghostchars
NPM · GHOSTCHARS
Find and remove invisible Unicode: zero-width, tag smuggling, bidi, homoglyphs. Offline.
Available components
Last scanned (8 hours ago)
Scores higher than 74% of npm servers
Category Developer Tools
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 24 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability68
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 973 tokens (~243/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Oct 26 +1
- Security disclosure: unverified → fail ▼ functional
- 14 Oct 26 0
- Security disclosure: fail → unverified ▼ functional
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
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 24 Oct 2026 · Analysed npm/ghostchars@1.0.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
check_paths ~234
Ghostchars: hold files on disk to a text-hygiene bar and report every file that would change, with exact character positions and the source line. This is the gate to run before committing. It reads only, and never writes.
| Name | Type | Req | Description |
|---|---|---|---|
| bar | string | – | Which bar the gate holds files to. "default" fails only on invisible characters, which nothing legitimately needs. "text" also fails on machine-writing typography. There is no "max" gate bar: it woul… |
| config | string | – | Path to a ghostchars.json. Auto-discovered if omitted. |
| max_files | integer | – | Stop after this many files. |
| max_findings_per_file | integer | – | Cap on the reported positions per failing file. |
| options | object | – | Precise per-option overrides. The bar sets the baseline and these can only turn individual options on. Leave this out unless you need a specific option. |
| paths | array | yes | Files or directories to check, relative to the server root. Pass the single file you just edited when you want a fast answer. |
| Name | Type | Req | Description |
|---|---|---|---|
| config | – | yes | The ghostchars.json that governed this run, or null when no config file was found and every file was held to the bar you asked for. |
| failures | array | yes | – |
| files_failing | integer | yes | – |
| files_scanned | integer | yes | – |
| files_skipped | integer | yes | – |
| ok | boolean | yes | – |
| root | string | yes | – |
| truncated | boolean | yes | – |
No examples provided.
clean_text ~306
Ghostchars: clean a piece of text. Removes invisible Unicode characters (zero-width spaces, word joiners, bidi controls, smuggled tag characters) and, at bar "text", normalises machine-writing typography to ASCII. Returns the whole cleaned text plus one finding per character it touched. Run it over any prose you are about to ship: documentation, a commit message, a pull request description, a release note, a UI string. Nothing leaves this machine.
| Name | Type | Req | Description |
|---|---|---|---|
| bar | string | – | How hard to clean. "text" (the default) removes invisible characters and normalises typography: no-break spaces to plain spaces, em and en dashes, curly quotes and ellipsis characters to ASCII. Use "… |
| max_findings | integer | – | Cap on the findings list and on the rewrite sites. The cleaned text is never truncated. |
| options | object | – | Precise per-option overrides. The bar sets the baseline and these can only turn individual options on. Leave this out unless you need a specific option. |
| text | string | yes | The text to clean. Returned unchanged if it is already clean. |
| Name | Type | Req | Description |
|---|---|---|---|
| changed | boolean | yes | True when cleaning would alter the text. |
| chars_after | integer | yes | – |
| chars_before | integer | yes | – |
| cleaned | string | – | The full cleaned text. Omitted when changed is false. |
| findings | array | yes | One entry per suspicious character, in document order. |
| findings_total | integer | yes | – |
| findings_truncated | boolean | yes | – |
| options_applied | array | yes | – |
| rewrite_sites | array | yes | Dash positions where rewriting the sentence beats the mechanical substitution. |
| rewrite_sites_total | integer | yes | How many rewrite sites the text holds, whether or not the list above was capped. |
| rewrite_sites_truncated | boolean | yes | – |
| summary | object | yes | – |
No examples provided.
inspect_text ~268
Ghostchars: list the suspicious characters in a piece of text without changing it. One row per character with line, column, codepoint, Unicode name, what the character is, and what a clean would do about it. Use it to see what is there before you decide, or to explain a finding to a person.
| Name | Type | Req | Description |
|---|---|---|---|
| bar | string | – | How hard to clean. "text" (the default) removes invisible characters and normalises typography: no-break spaces to plain spaces, em and en dashes, curly quotes and ellipsis characters to ASCII. Use "… |
| max_findings | integer | – | Cap on the findings list. The total is always reported. |
| options | object | – | Precise per-option overrides. The bar sets the baseline and these can only turn individual options on. Leave this out unless you need a specific option. |
| text | string | yes | The text to examine. It is never modified. |
| Name | Type | Req | Description |
|---|---|---|---|
| by_kind | array | yes | – |
| clean | boolean | yes | – |
| findings | array | yes | One entry per suspicious character, in document order. |
| returned | integer | yes | – |
| summary | object | yes | – |
| total | integer | yes | – |
| truncated | boolean | yes | – |
No examples provided.
style_report ~100
Ghostchars: measure the habits that make a draft read as machine written. Sentence-length uniformity, stock transitions, tell words, em dash density, tricolons, hedging, and missing specifics. This is not a detector: it does not decide whether a text was generated, and it emits no probability and no score. Use it to find the sentences worth rewriting.
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | The draft to measure. Prose, not code. |
| Name | Type | Req | Description |
|---|---|---|---|
| bold_lead_bullets | integer | yes | – |
| bullets | integer | yes | – |
| contractions_per_1000 | number | yes | – |
| em_dashes_per_1000 | number | yes | – |
| first_person_per_1000 | number | yes | – |
| headings | integer | yes | – |
| hedges_per_1000 | number | yes | – |
| not_x_but_y | integer | yes | – |
| numbers_per_1000 | number | yes | – |
| observations | array | yes | – |
| paragraph_shape | object | – | – |
| paragraphs | integer | yes | – |
| proper_nouns_per_1000 | number | yes | – |
| sentence_initial_transitions | object | yes | – |
| sentence_length | object | – | – |
| sentences | integer | yes | – |
| summary | object | yes | – |
| tell_density_per_1000 | number | yes | – |
| tell_phrases | object | yes | – |
| tell_words | object | yes | – |
| tricolons | integer | yes | – |
| words | integer | yes | – |
No examples provided.
How do I install the Ghostchars MCP server?
Ghostchars runs locally as an npm package, launched with npx -y ghostchars. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · ghostchars
claude mcp add ghostchars-ghostchars -- npx -y ghostchars
What is the Ghostchars MCP server?
Ghostchars is an MCP server listed in the public MCP registry as io.github.ghostchars/ghostchars. Find and remove invisible Unicode: zero-width, tag smuggling, bidi, homoglyphs. Offline. This page covers its npm package (ghostchars).
Is the Ghostchars MCP server safe to use?
Ghostchars scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 October 2026. It declares no install or post-install scripts. 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 Ghostchars MCP server expose?
Ghostchars exposes 4 tools: clean_text, inspect_text, style_report, check_paths. Their descriptions and schemas cost roughly 908 tokens of context every time the server is loaded.
Is the Ghostchars MCP server still maintained?
Ghostchars is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Ghostchars MCP server under?
Ghostchars declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.