TypeSafe MCP
PYPI · TYPESAFE-MCP · SCANNED SEP 22
Host-neutral MCP bridge for TypeSafe AI Jev judgments with typed review, routing, and gate tools.
Available components
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 Security44
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs a script at install time (build_backend,cmdclass) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does. View diagnostics → Partial
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency23
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- 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 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 618 tokens (~68/item across 9 items; 9 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage74
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 8% of tool parameters carry a description.Partial
- 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 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.
How do I install the TypeSafe MCP server?
TypeSafe MCP runs locally as a PyPI package, launched with uvx typesafe-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · typesafe-mcp
claude mcp add renwang-huang-typesafe-mcp -- uvx typesafe-mcp
{
"mcpServers": {
"renwang-huang-typesafe-mcp": {
"command": "uvx",
"args": [
"typesafe-mcp"
]
}
}
} {
"servers": {
"renwang-huang-typesafe-mcp": {
"command": "uvx",
"args": [
"typesafe-mcp"
]
}
}
} codex mcp add renwang-huang-typesafe-mcp -- uvx typesafe-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"renwang-huang-typesafe-mcp": {
"type": "local",
"command": [
"uvx",
"typesafe-mcp"
],
"enabled": true
}
}
} openclaw mcp add renwang-huang-typesafe-mcp --command uvx --arg typesafe-mcp
mcp_servers:
renwang-huang-typesafe-mcp:
command: "uvx"
args: ["typesafe-mcp"] {
"McpServers": {
"renwang-huang-typesafe-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"typesafe-mcp"
]
}
}
} assistant mcp add renwang-huang-typesafe-mcp -t stdio -c uvx -a typesafe-mcp
{
"mcpServers": {
"renwang-huang-typesafe-mcp": {
"command": "uvx",
"args": [
"typesafe-mcp"
]
}
}
} 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.
- 22 Sept 26 −5
- Source repository: pass → fail ▼ security
- 21 Sept 26 50
First indexed and scored.
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 22 Sept 2026 · Analysed pypi/typesafe-mcp@0.5.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 2 scripts
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
| cmdclass | unreviewed | <custom, unreviewed> |
Background: Why install scripts are a supply-chain risk →
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 ~50
Estimate the probability that a bounded yes/no proposition is true.
| Name | Type | Req | Description |
|---|---|---|---|
| false_criteria | – | – | – |
| instructions | – | yes | – |
| model | string | – | – |
| state | – | yes | – |
| true_criteria | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| answer | object | yes | – |
| evaluation | object | yes | – |
| model | string | yes | – |
| type | – | yes | – |
| usage | object | yes | – |
No examples provided.
classify ~44
Choose one label from a closed set and return its probability distribution.
| Name | Type | Req | Description |
|---|---|---|---|
| instructions | – | yes | – |
| labels | object | yes | – |
| model | string | – | – |
| state | – | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| answer | object | yes | – |
| evaluation | object | yes | – |
| model | string | yes | – |
| type | – | yes | – |
| usage | object | yes | – |
No examples provided.
evaluate ~82
Evaluate state with TypeSafe Jev and return the raw typed answers. Use for bounded noul, choice, or score questions; never for prose, code generation, arithmetic, or dates.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | – | Optional model id or alias. |
| questions | object | yes | Map of question id to a TypeSafe question. |
| state | – | yes | Text or structured evidence. |
| Name | Type | Req | Description |
|---|---|---|---|
| answers | object | yes | – |
| model | string | yes | – |
| usage | object | yes | – |
No examples provided.
gate ~73
Evaluate bounded pass checks and turn their probabilities into pass/review/fail. This is not an authorization or security boundary; keep normal human and policy controls.
| Name | Type | Req | Description |
|---|---|---|---|
| checks | object | yes | – |
| model | string | – | – |
| pass_at | number | – | – |
| review_at | number | – | – |
| state | – | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| checks | object | yes | – |
| decision | – | yes | – |
| evaluation | object | yes | – |
| policy | object | yes | – |
| type | – | yes | – |
No examples provided.
health ~35
Inspect local MCP configuration without making a network request. Set live=true only for an explicit paid provider check.
| Name | Type | Req | Description |
|---|---|---|---|
| live | boolean | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| api_key_configured | boolean | yes | – |
| base_url | string | – | – |
| live | boolean | yes | – |
| max_retries | integer | – | – |
| model | string | – | – |
| server | string | yes | – |
| status | string | – | – |
| timeout_seconds | number | – | – |
| type | – | yes | – |
| version | string | yes | – |
No examples provided.
review ~67
Evaluate a diff, plan, or test report against checks and return pass/review/fail signals. It never edits files.
| Name | Type | Req | Description |
|---|---|---|---|
| checks | object | yes | – |
| model | string | – | – |
| pass_at | number | – | – |
| review_at | number | – | – |
| state | – | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| checks | object | yes | – |
| decision | – | yes | – |
| evaluation | object | yes | – |
| policy | object | yes | – |
| type | – | yes | – |
No examples provided.
route ~51
Choose the next action from a closed set. This suggests an action; it does not execute it.
| Name | Type | Req | Description |
|---|---|---|---|
| actions | object | yes | – |
| instructions | – | – | – |
| model | string | – | – |
| state | – | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| answer | object | yes | – |
| evaluation | object | yes | – |
| model | string | yes | – |
| route | string | yes | – |
| type | – | yes | – |
| usage | object | yes | – |
No examples provided.
score ~48
Rate state on an ordered rubric and return the weighted score, probabilities, and confidence.
| Name | Type | Req | Description |
|---|---|---|---|
| instructions | – | yes | – |
| levels | array | yes | – |
| model | string | – | – |
| state | – | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| answer | object | yes | – |
| evaluation | object | yes | – |
| model | string | yes | – |
| type | – | yes | – |
| usage | object | yes | – |
No examples provided.
verify ~61
Check several claims against the supplied evidence in one request. Results are review signals, not proof of truth.
| Name | Type | Req | Description |
|---|---|---|---|
| claims | object | yes | – |
| false_criteria | – | – | – |
| model | string | – | – |
| state | – | yes | – |
| true_criteria | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| answers | object | yes | – |
| evaluation | object | yes | – |
| type | – | yes | – |
No examples provided.
What is the TypeSafe MCP server?
TypeSafe MCP is listed in the public MCP registry as io.github.Renwang-Huang/typesafe-mcp. Host-neutral MCP bridge for TypeSafe AI Jev judgments with typed review, routing, and gate tools. This page covers its PyPI package (typesafe-mcp).
Is the TypeSafe MCP server safe to use?
TypeSafe MCP scores 45 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 2026. 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 TypeSafe MCP server expose?
TypeSafe MCP exposes 9 tools: evaluate, classify, score, check, verify, and 4 more. Their descriptions and schemas cost roughly 511 tokens of context every time the server is loaded.
Is the TypeSafe MCP server still maintained?
TypeSafe MCP is still listed as active in the MCP registry. We last reached this channel on 22 September 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 TypeSafe MCP server under?
TypeSafe MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.