GLM MCP
NPM · GLM-MCP · SCANNED OCT 1
GLM (Zhipu/Z.ai) as a ~10x cheaper file-editing subagent for AI coding agents.
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 Security98
- 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
- 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
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 79 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability65
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 675 tokens (~225/item across 3 items; 3 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 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
How do I install the GLM MCP server?
GLM MCP runs locally as an npm package, launched with npx -y glm-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · glm-mcp
claude mcp add djerok-glm-mcp -- npx -y glm-mcp
{
"mcpServers": {
"djerok-glm-mcp": {
"command": "npx",
"args": [
"-y",
"glm-mcp"
]
}
}
} {
"servers": {
"djerok-glm-mcp": {
"command": "npx",
"args": [
"-y",
"glm-mcp"
]
}
}
} codex mcp add djerok-glm-mcp -- npx -y glm-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"djerok-glm-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"glm-mcp"
],
"enabled": true
}
}
} openclaw mcp add djerok-glm-mcp --command npx --arg -y --arg glm-mcp
mcp_servers:
djerok-glm-mcp:
command: "npx"
args: ["-y", "glm-mcp"] {
"McpServers": {
"djerok-glm-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"glm-mcp"
]
}
}
} assistant mcp add djerok-glm-mcp -t stdio -c npx -a -y glm-mcp
{
"mcpServers": {
"djerok-glm-mcp": {
"command": "npx",
"args": [
"-y",
"glm-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.
- 1 Oct 26 0
- Stability: 0.97 → pass security
- 30 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Sept 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Sept 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.
- 25 Sept 26 −3
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 0
- Stability: 0.97 → pass security
- 23 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
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 1 Oct 2026 · Analysed npm/glm-mcp@1.3.0
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 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 31 |
| 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 →
glm_agent Run GLM as a file-accessing agent ~330
Run GLM as a real coding agent with its OWN file tools (read/write/edit/list/bash); it works your repo end-to-end on GLM tokens (~10x cheaper than Opus). Prefer this over doing repo work yourself; it also handles text-only subtasks (give it a task with no file edits). Pass task + absolute workdir. Returns a concise summary+stats (use dry_run to preview a diff first). Not for sensitive, huge-context, or heavy dependent-tool-loop work.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Optional extra context/constraints (GLM can also read files itself). |
| dry_run | boolean | – | If true, GLM proposes a diff and writes nothing (preview before applying). Default false. |
| format | string | – | concise (default: summary+stats+changed files) or detailed (adds full diff). dry_run always shows the diff. |
| max_tokens | – | – | 'auto' (default): uncapped/generous per turn — you (the orchestrating agent) decide. Pass a number (256–131072) to cap each turn. (GLM_CAP=on enforces a hard limit regardless.) |
| model | string | – | Model id or 'auto' (default, peak-aware). |
| task | string | yes | The coding task for GLM to carry out end-to-end in the repo. |
| thinking | boolean | – | Enable GLM reasoning mode for harder tasks. Default false. |
| workdir | string | – | Absolute path to the project root GLM should operate in. Defaults to the server's cwd; always pass it explicitly. |
No output schema declared.
No examples provided.
glm_recommend Recommend GLM vs Opus for a task ~306
Free local advisory (no GLM call): given a task profile, returns GLM-vs-Opus, model, confidence, and reasons. Call when unsure which engine to use.
| Name | Type | Req | Description |
|---|---|---|---|
| chinese | boolean | – | True if Chinese or Chinese-English bilingual (GLM strength, +1). |
| complexity | string | – | Default 'medium'. |
| input_tokens | integer | – | Approx context size needed. >128K forces Opus (GLM degrades past ~100K). |
| latency_sensitive | boolean | – | True if a tight interactive loop (forces Opus). |
| long_horizon | boolean | – | True if many sequential steps / multi-hour autonomy. |
| needs_parallel | boolean | – | True if it needs several concurrent agents (forces Opus). |
| sensitive | boolean | – | True if proprietary/security-critical (forces Opus). |
| steps | integer | – | Approx number of dependent sequential steps. >20 forces Opus (goal drift). |
| task_type | string | – | Closest task category. Default 'general'. |
| tool_pattern | string | – | Tool-use shape: single one-shot call / short independent fanout (GLM-ok) vs heavy dependent agentic loop (forces Opus). |
| unfamiliar_api | boolean | – | True if it uses a niche/post-cutoff/internal API GLM can't know (-2; paste docs or use Opus). |
| vision | boolean | – | True if input includes images/screenshots/GUI/computer-use (forces Opus). |
No output schema declared.
No examples provided.
glm_status GLM status & config ~39
Free local status: peak window, active model, GLM usage ledger (proof of GLM tokens spent), and config health. No GLM call.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the GLM MCP server?
GLM MCP is listed in the public MCP registry as io.github.djerok/glm-mcp. GLM (Zhipu/Z.ai) as a ~10x cheaper file-editing subagent for AI coding agents. This page covers its npm package (glm-mcp).
Is the GLM MCP server safe to use?
GLM MCP scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 1 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 GLM MCP server expose?
GLM MCP exposes 3 tools: glm_agent, glm_recommend, glm_status. Their descriptions and schemas cost roughly 675 tokens of context every time the server is loaded.
Is the GLM MCP server still maintained?
GLM MCP is still listed as active in the MCP registry. We last reached this channel on 1 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 GLM MCP server under?
GLM 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.