Span
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Keep the understanding your agent worked for
A coding agent traces a request across services, checks the tests, finds the contract, and explains why the boundary exists. The next session should be able to find that explanation and see whether its support still holds.
Span makes that investigation reusable. It is a local MCP server where agents record coherent explanations with exact source support, explicit gaps, and version history. Later agents can discover the explanation through an ordinary engineering question, then inspect what is current, disputed, or changed.
The coding agent does the thinking. Span keeps the record and checks its support.
Related MCP server: Estelle
How it works
Investigate a real question. Ask over the relevant scope. Span returns qualified saved candidates or inspectable source evidence and an honest gap.
Record the useful result. Save conclusions across the files you actually examined, with their support and unanswered questions. Work that started outside Span can be recorded directly after evidence admission.
Reuse in a fresh session. Ask the next engineering question, discover applicable understanding, and retrieve it with live support and challenges.
Reassess after change. Check affected dependencies, investigate what changed, then confirm, correct, replace, or withdraw the explanation. Earlier versions remain inspectable.
One explanation can span code, tests, CSS, configuration, and contracts. The agent decides what is worth recording; a file inventory does not become a mandatory documentation campaign.
See the lifecycle
Illustrative tool sequence, not literal request JSON. The installed schemas and MCP reference own the wire grammar.
understand_question: "How does checkout decide whether to charge?"
→ InvestigationNeeded: exact evidence and an explicit gap
agent investigates; evidence_extend admits the additional sources
record_create: explanation + admitted support + remaining questions
→ committed receipt, understanding version 1, support qualification
fresh session asks: "Where is purchase eligibility decided?"
→ associated saved candidates; agent checks applicability
understand_retrieve
→ recorded explanation, live support, gaps, and challenges
supporting source changes
reassess
→ REASSESSMENT_REQUIRED with the affected dependencies
agent investigates and records a correction against the expected version
→ version 2; version 1 remains historySource association and term overlap help discovery. A different wording can find saved understanding without its original ID, but semantic equivalence is not guaranteed. A candidate is a starting point for judgment.
Know what can be reused
Qualification | What the agent can conclude |
| The declared support still passes its checks. Applicability and semantic correctness still need judgment. |
| Source, authority, premise, or recorded membership support changed. Revisit the affected explanation. |
| Required support cannot be established. The limitation stays explicit. |
Gaps and challenges remain visible independently of support currency. Matching bytes do not settle a dispute, and test existence does not establish a pass. Independent verification records the observations actually tested and preserves failures as failures.
Recording is atomic and returns a receipt. The caller preserves identity before sending; retrying the same identity and content recovers the retained receipt after a lost response or process restart. A committed receipt and a present support qualification answer different questions.
Quick start
The verified installation path is Linux with Python 3.12+, Node.js, and npm. From a checkout containing the 0.9.0 candidate:
python3 scripts/install-span.py --repo /path/to/your/repoFor a published package release, install span-mcp with your Python package
manager and run span-install --repo /path/to/your/repo. See
install and connect for registration, verification, and the
offline store transition.
The installer provisions the managed structural indexer, runtime, skills, and host integration. Reconnect your coding agent after upgrade so it receives the new tools and instructions. Verify operational setup with:
span-install --verify-onlySetup creates no understanding. Begin with a question from your actual task; see using Span.
Beta host status
Host | Current scope |
Codex | Live beta validation target; packaged lifecycle calls work with hooks explicitly disabled. |
OpenCode | Managed integration remains implemented; earlier trials are not final-package revalidation. |
Claude Code | Managed integration remains implemented; live model grammar and caller identity are UNVERIFIED under the owner waiver. |
Other MCP hosts | Manual stdio connection is available; model-delivery behavior needs host-specific verification. |
Registration, hook configuration, and model-delivered behavior are distinct. Optional hooks provide notices; retrieval and recording still check support when hooks are absent. See host integration.
Fits around your agent
Span runs locally over stdio and keeps state outside target repositories. Your agent uses its own model, tools, edits, and test runner. Span does not invoke a model or store provider credentials. Structural search helps investigation; recorded conclusions retain the agent's interpretation and declared support.
The intended benefit is continuity between sessions and a focused review of changed support. Recording and host delivery have costs. This beta makes no universal time/token-saving claim or completed comparative product-fitness ACCEPT claim. See acceptance.
Status and documentation
This checkout describes 0.9.0 beta: nineteen lifecycle tools, schema-10 storage, explicit offline transition, and live support qualification. macOS and Windows installation paths remain unverified. Publication and product acceptance are separate from the implementation version.
Older acceptance evidence retains its historical protocol and does not certify the rebuilt API or comparative value.
Contributing
See contributing. Preserve the central contract: useful understanding stays attached to its support, noncurrent or uncertain state stays explicit, and corrections preserve history. Security reports go through SECURITY.md; support expectations are in SUPPORT.md.
Registry
Official MCP Registry entry: io.github.pontivus-com/span
mcp-name: io.github.pontivus-com/span
License
Span is licensed under Apache License 2.0 (Apache-2.0). See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared memory for coding agents. Stop re-explaining your codebase every session.
Cache source-backed repository context so coding agents can reuse knowledge across sessions.
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Persistent engineering memory designed to follow developers across coding agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides AI coding agents with persistent architectural memory of codebases, enabling impact analysis, test generation, and code generation with reduced token usage.MIT
- AlicenseNot gradedqualityAmaintenanceProvides persistent memory for coding agents and grounds their claims by verifying against the actual codebase, preventing hallucinated responses.506 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables agentic coding tools to maintain a living, in-repo model of intent, architecture, and code, with deterministic indexing, bidirectional linking, and continuous drift detection for task-scoped context and reconciliation.MIT
- AlicenseNot gradedqualityBmaintenanceProvides AI coding agents with fast, deterministic access to code graphs, knowledge lifecycle state, and cross-document symbol links, enabling compact context retrieval and seamless session handoffs.1MIT