Skip to main content
Glama
contextstream

ContextStream MCP Server

Agent Q&A

qa
Read-onlyIdempotent

Ask workspace-specific questions about prior decisions, conventions, runbooks, and guardrails. Receive grounded answers with source citations from your project's knowledge base.

Instructions

ContextStream agent Q&A — ask the workspace/project knowledge base when you get stuck.

When to use:

  • You need workspace-specific knowledge you cannot derive from code: prior decisions ("why was X chosen over Y?"), conventions ("what's the file naming pattern in this repo?"), runbooks ("how does the team handle this kind of incident?"), guardrails ("what's off-limits in this workspace?").

  • You're about to make a non-trivial choice and the workspace probably has prior context that shapes it.

  • A teammate has likely answered this before and you'd rather reuse than re-derive.

When NOT to use:

  • General programming questions you can answer yourself or via web search ("how does Rust async work?").

  • Things you can determine by reading the code right in front of you — read it first.

  • Trivial syntax or single-line questions.

Not a reflex, not a last resort. If you're spending more than ~30 seconds stuck on something workspace-shaped, ask. If you can find the answer in 30 seconds yourself, do that.

Actions:

  • ask: submit a question, get a grounded answer with citations + confidence.

  • search: vector-similarity-free listing of prior Q&A — check before re-asking.

  • save_kb: store guidance/guardrail/faq/runbook/caveat for future asks to reference.

  • list_kb: browse stored knowledge.

  • get_kb / update_kb / delete_kb: manage individual KB items.

  • feedback: rate an answer (-1, 0, +1) so future retrievals weight it appropriately.

Answers come from ContextCode, ContextStream's grounded Q&A agent. Every claim cites the source ([id=decision:abc] / [id=lesson:xyz] / [id=qa_kb_item:def] etc.) so you can verify before acting on it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoKB item id (action=get_kb / update_kb / delete_kb)
tagNoFilter by tag (action=search, list_kb)
kindNoKB item kind (action=save_kb / update_kb)
pageNoPage number (1-based)
tagsNoTags to attach to the persisted question (action=ask)
queryNoFree-text filter against prior Q&A question text (action=search) or KB title/content (action=list_kb)
scoreNoFeedback score: -1, 0, or +1 (action=feedback)
titleNoKB item title (action=save_kb / update_kb)
actionYesAction to perform
contentNoKB item body (action=save_kb / update_kb)
metadataNoOptional metadata (action=save_kb / update_kb)
per_pageNoPage size
questionNoNatural-language question (action=ask)
answer_idNoAnswer id to rate (action=feedback)
created_byNoFilter KB items by creator user id (action=list_kb)
max_tokensNoOverride max answer tokens (action=ask)
project_idNoProject ID (UUID).
session_idNoOptional MCP session id — links the question to the AI session that asked
temperatureNoOverride sampling temperature (action=ask, default 0.2)
workspace_idNoWorkspace ID (UUID).
scope_summaryNoHuman-readable scope label fed into the prompt (e.g. 'workspace=Engineering, project=api')
asked_by_user_idNoFilter prior Q&A by who asked (action=search)
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description lists write actions (save_kb, update_kb, delete_kb) but annotations declare readOnlyHint=true, a direct contradiction. Despite other useful details (citations, confidence, feedback), the contradiction severely undermines transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections for intro, usage guidelines, heuristic, actions list, and answer explanation. Front-loaded with purpose. Slightly verbose but each part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all actions, explains knowledge base concept, answer generation, citation format, feedback mechanism. Without output schema, description still provides enough context for the agent to understand return values (grounded answer with citations).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so baseline is 3. Description adds value by explaining each action's purpose (e.g., 'search: vector-similarity-free listing of prior Q&A'), enhancing understanding of parameter usage beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it's for asking the workspace/project knowledge base. It distinguishes from sibling tools like 'search' and 'session' by explicitly saying it's for workspace-specific knowledge, not general programming or code-reading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Extensive when-to-use (workspace-specific knowledge, prior decisions, conventions, runbooks) and when-not-to-use (general programming, things in code, trivial syntax) guidance. Includes a heuristic (~30 seconds stuck) and explicitly says it's not a reflex or last resort.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/contextstream/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server