1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@scry list all active design entries" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

scry

by prmichaelsen

Overview Schema Related Servers Score Discussions

Python

Local

scry

Scry Marker Specification - This project implements a formal, generic scry marker contract defined here

See scryspec.com for an overview.

Marker-indexed SQL cache MCP server. Scry indexes in-file @scry.* markers into a SQLite database that agents query via read-only SQL, providing structured project knowledge without LLM reasoning.

PyPI Python

Install

uv pip install scry-mcp
# or:
pip install scry-mcp

The PyPI distribution is scry-mcp (the bare name scry was already taken on PyPI). The import name and the installed console command are both scry.

Related MCP server: code-index

Quickstart

# In your project root:
scry init                # scaffolds agent/ + driver dirs, updates .gitignore

Then add it to your MCP client config:

{
  "mcpServers": {
    "scry": {
      "command": "scry"
    }
  }
}

The MCP client inherits cwd from wherever it's launched, and scry walks up from there looking for an agent/ directory — so the same config works for any project. Bare scry (no subcommand) starts the MCP server over stdio — that's what Claude calls. Other subcommands:

Command	Purpose
`scry`	Run the MCP server (default).
`scry init [path]`	Create `agent/` + `agent/drivers/@local/scry/{data,runtime,scripts}/` and a local `.gitignore` inside the driver dir. Idempotent — safe to run inside an ACP project.
`scry surface [--force]`	One-shot batch reindex without booting the server.
`scry version`	Print the package version.

The server walks up from cwd until it finds an agent/ directory; that becomes the project root. The cache lives at agent/drivers/@<namespace>/scry/data/project.db and is gitignored.

Markers

Scry recognizes three marker kinds per scry-spec v1.2.0: @scry.entry and @scry.anchor are block markers with a YAML body between open/close tokens; @scry.bind is a line or block marker declaring cross-references.

<!-- @scry.entry
id: design.auth-flow~a1b2c3d4
kind: design
summary: >
  JWT auth middleware, token validation, refresh flow
status: active
weight: 0.85
tags: ["scope:auth", "topic:security"]
rationale: >
  Missing this causes auth bypass bugs
applies: modifying auth, adding protected endpoints
seeded_questions:
  - How does token refresh work?
extras:
  owner: auth-team
  jira: AUTH-1247
  reviewed_at: 2026-05-19
@scry.entry.end -->

<!-- @scry.anchor auth-check~f1e2d3c4
description: JWT validation point for protected routes
@scry.anchor.end -->

# @scry.bind validate-jwt~a1b2c3d4 spec.auth~xyz89012#FR3
# @scry.bind jwt-expiry~b2c3d4e5 spec.auth~xyz89012#UT1

Block markers can be embedded in any host-language comment style (HTML, Python, JS, JSDoc, Rust, bare YAML). Comment prefixes are inferred from the YAML body — there is no per-language config.

`extras` field (scry-spec v1.2.0, FR4.B)

@scry.entry accepts an optional extras field: a single-depth map of arbitrary string keys to scalar values (string | number | boolean | null). Use it to attach structured metadata that isn't part of the core schema — ownership, ticket IDs, cost ledgers, review timestamps, anything you want to query later.

Constraints:

Single depth only — values must be scalars; nested maps and lists are diagnostic violations.
Serialized size ≤ 4 KB (the spec's SHOULD-level cap).
Oversize payloads MUST round-trip intact — the cap is a diagnostic, not a truncation gate. Empty extras: {} emits a SHOULD-level warning.

Indexed and queryable as of v0.17.0. The extras field is serialized to compact JSON-text in the scry__doc.extras column (NULL when absent), and exposed to scry_sql via SQLite JSON1. A doc with

extras:
  cost_usd: 12.5
  tier: gold
  active: true

answers queries like:

SELECT id,
       json_extract(extras, '$.cost_usd') AS cost,
       json_extract(extras, '$.tier')     AS tier
FROM scry__doc
WHERE kind = 'deliverable'
  AND json_extract(extras, '$.active') = 1
ORDER BY cost DESC;

Round-trip is byte-equivalent for the YAML scalar map: integers, floats, strings, booleans, and null are preserved.

`@scry.entry` kind values (v1.2.0 baseline)

kind	use for
`design`	architecture and design docs
`pattern`	canonical recipes, established patterns
`spec`	requirements and specifications
`lesson`	post-mortems, "I tried X and it failed because Y"
`internal`	service quirks, undocumented behaviors
`task`	discrete work items
`milestone`	phase markers, exit criteria
`goal`	objective satisfied by a deliverable set via the `satisfies` typed edge (v1.2.0)
`report`	wake/session reports
`audit`	security or integrity audits
`research`	research notes
`code`	implementation-specific docs

MCP tools

Tool	Purpose
`scry_sql(query)`	Read-only SQL gateway. Rejects mutator keywords. Returns `{results, row_count}` JSON.
`scry_grep(query, kind?, status?, path_glob?, limit?)`	Full-text search over indexed file bodies (`scry__file_fts`). Complements `scry_sql` when you want to search prose, not just marker fields.
`scry_mint(kind, prefix)`	Generate a collision-free ID and the marker schema.
`scry_mint_with_check(kind, prefix)`	Preferred minter — same as `scry_mint` plus tier-1/tier-2 collision warnings.
`scry_surface(force=false, path?)`	Batch reindex from disk. `force=true` hard-deletes records whose source file no longer exists; `path` scopes the walk to a single file or subdirectory.
`scry_sink(then_surface=false)`	Lower the index back to disk-only state — truncates all index tables atomically (schema preserved, disk markers untouched). Requires user confirmation; `then_surface=true` rebuilds in one call.
`scry_scrub()`	Create a `<branch>--clean` git branch with all `@scry.*` markers stripped from non-agent files.
`scry_script(action, script?, params?)`	Discover and run validation scripts from `src/scry/scripts/` and `agent/drivers/@<ns>/scry/scripts/`.
`scry_db_health()`	Probe the project DB and report `status` ∈ {`ok`, `corrupt`, `locked`}, `integrity_check` result, and `scry__doc` row count. For substrate auto-restore loops that need to distinguish corruption from transient WAL write-lock contention.

Database schema

Marker-backed core tables:

Table	Holds
`scry__doc`	One row per `@scry.entry` marker — id, kind, status, weight, summary, rationale, applies, current_path, ephemeral, missing_since, content_hash, extras, timestamps.
`scry__doc_tag`	Tags as a join table — `(doc_id, tag)`.
`scry__doc_seeded_question`	Seeded questions per doc — `(doc_id, ordinal, question)`.
`scry__anchor`	One row per `@scry.anchor` marker — id, doc_id, description, content_hash, timestamps.
`scry__anchor_seeded_question`	Seeded questions per anchor — `(anchor_id, ordinal, question)`.
`scry__bind`	One row per `@scry.bind` marker — source_doc_id, source_local_id, target_id, target_fragment, comment, content_hash, timestamps.
`scry__rel`	Typed edges between docs — `(from_id, to_id, predicate, fragment)`. Predicates: `depends_on`, `implements`, `supersedes`. Cycle detection enforced on `depends_on`.
`scry__file`	Universal file-body index — `(path, doc_id, body, content_hash, last_modified)`. Populated during `scry_surface`.
`scry__warning`	Lint-style warnings emitted by the parser/indexer — id, kind, marker_kind, marker_id, file_path, message, detected_at.
`migration`	Schema migration ledger.

FTS5 virtual tables (trigger-maintained, queryable via FTS MATCH):

FTS table	Searches
`scry__doc_fts`	Doc summary, rationale, applies, current_path.
`scry__doc_tag_fts`	Tag strings.
`scry__doc_seeded_question_fts`	Doc seeded questions.
`scry__anchor_fts`	Anchor descriptions.
`scry__bind_fts`	Bind source_local_id, target_id, comment.
`scry__file_fts`	Full file bodies. Prefer the `scry_grep` tool over hand-rolled queries.

The cache is fully reconstructable from disk via scry_surface. The DB is gitignored; after git pull, agents call scry_surface to rebuild.

Watcher

A daemon thread runs alongside the MCP server, watching the project tree with a 150 ms debounce window. A lock file at agent/drivers/@<ns>/scry/runtime/lock performs PID-based primary election so multiple sessions don't race writes. The primary instance runs a cold scan on startup; secondaries observe and wait.

On file deletion: docs are soft-deleted (missing_since set); anchors and binds are hard-deleted.

Tests

uv pip install -e ".[dev]"
pytest

159 tests cover the parser, SQL gateway, mint, surface, watcher plumbing, script discovery, relationship cycle detection, FR4.B extras indexing + JSON1 queryability, schema-migration backfill, and concurrent-connection retry behavior.

License

MIT — see LICENSE.

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

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/prmichaelsen/scry'

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

scry

Install

Quickstart

Markers

extras field (scry-spec v1.2.0, FR4.B)

@scry.entry kind values (v1.2.0 baseline)

MCP tools

Database schema

Watcher

Tests

License

Maintenance

Resources

Looking for Admin?

Latest Blog Posts

MCP directory API

`extras` field (scry-spec v1.2.0, FR4.B)

`@scry.entry` kind values (v1.2.0 baseline)