context-guardian
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GUARDIAN_HOST | No | Interface the running Context Guardian proxy binds; the MCP server reads the proxy's `/guardian/stats` over this host. Leave this alone unless you know what you are doing. | 127.0.0.1 |
| GUARDIAN_PORT | No | Port the running Context Guardian proxy listens on; the MCP server reaches it at `GUARDIAN_HOST`:`GUARDIAN_PORT` for `guardian_status`. | 8786 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_proxy_statusA | Proxy up and compacting? window, budget, compactions, tokens saved. Use list_spans, search_spans or read_span for archived conversation text. One GET to /guardian/stats, 3 s. Returns those stats. |
| list_digestsA | Skim the archive: a line per span, newest first, within max_tokens. Use search_spans for words, read_span to open. Local files, no network. Returns |
| list_spansA | Browse the span archive, no search term. Use search_spans for known text, read_span to open one. Local files, no network. Returns |
| search_spansA | Find words in archived conversation, best match first. Use list_spans to browse, read_span to open a hit. Local files, no network. Returns |
| read_spanA | One span's summary and original messages, verbatim, or messages start..end. Use list_spans or search_spans first. One local file, no network. Returns |
| get_seal_statusA | Verify the sealed archive: hash chains against files. Use list_spans for run ids. Local files, no network. Returns |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a distinct role: browsing runs/spans, searching text, reading one span, checking seal integrity, and checking proxy stats. The main overlap is between list_digests and list_spans, both of which browse the archive, but their descriptions clarify different granularity and output.
All tool names use consistent snake_case with a verb_noun structure: list_*, search_*, read_*, and get_*_status. The pattern is predictable and easy to parse.
Six tools is well-scoped for an archive browsing and status-checking server. Each tool covers a distinct operation, and none feels redundant or extraneous.
The surface covers listing, skimming, searching, reading spans, verifying seal integrity, and checking proxy status. Minor gaps such as run-level metadata or explicit archive export are not essential for the apparent purpose, so agents can still complete core workflows.